© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11056
    Prev
    Next
    INDEX
    Explanations

    prime numbers and code syntax

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

    This neuron fires on content-bearing words (not common function words), i.e. informative nouns, verbs, and technical terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    ربة
    0.79
    നിന്ന്
    0.77
    يكم
    0.74
    ু
    0.73
    adır
    0.73
     Remarks
    0.73
     Aguas
    0.73
     düşünüyorum
    0.73
     καὶ
    0.71
     esemplare
    0.71
    POSITIVE LOGITS
    +"
    0.81
    ಗೆ
    0.76
    nl
    0.74
    xel
    0.71
    na
    0.69
    nial
    0.69
    irc
    0.68
    ch
    0.67
    ("
    0.67
    AL
    0.66
    Activations Density 0.000%

    No Known Activations