© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8160
    Prev
    Next
    INDEX
    Explanations

    you need to do

    np_acts-logits-general · gemini-2.5-flash-lite

    The main thing this neuron does is spot numeric and quantitative expressions—numbers, dates, percentages, measurements, and similar tokens indicating quantities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the phrase "For example" followed by illustrative details or scenarios.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    statements that introduce an illustrative example or specific instance (e.g., “for example,” “for instance”) and the ensuing explanatory details.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Also
    0.80
     కూడా
    0.80
     نیز
    0.80
     tambien
    0.79
     également
    0.79
     অন্তত
    0.77
     بھی
    0.77
     также
    0.77
     Also
    0.76
     myös
    0.75
    POSITIVE LOGITS
     مثلا
    1.23
     misalnya
    1.16
     Suppose
    1.13
    Suppose
    1.09
     suppose
    1.05
     เงี้ย
    1.03
     digamos
    1.02
     například
    1.02
     say
    1.01
     mesela
    0.96
    Activations Density 0.420%

    No Known Activations