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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15562
    Prev
    Next
    INDEX
    Explanations

    cover with water

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

    The main thing this neuron does is detect floating-point numerical values (numbers containing a decimal point).

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

    the word "from" in contexts related to video content, embedded media, or digital sources.

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

    mentions of analytics/reporting and other metadata-like fields (attribution, duration, sections) within documents.

    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_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
    ان
    1.08
    UC
    0.76
    quirements
    0.76
     пе
    0.75
    Actress
    0.75
    bio
    0.74
    Client
    0.74
    نامه
    0.74
    iterations
    0.73
    මෙ
    0.73
    POSITIVE LOGITS
     walnuts
    0.93
     hateful
    0.90
     fright
    0.89
     eleventh
    0.89
     seventh
    0.88
     evenings
    0.88
     ammonia
    0.88
     ammonium
    0.88
     basalt
    0.87
     irradiance
    0.87
    Activations Density 0.001%

    No Known Activations