© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6547
    Prev
    Next
    INDEX
    Explanations

    Immediately Invoked Function, Life Token, Double, Colors

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

    The neuron activates on floating‐point numeric tokens (numbers with a decimal point).

    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
    NES
    0.79
     alienated
    0.79
    ှ
    0.76
    ao
    0.76
    orf
    0.73
    ogs
    0.73
    east
    0.73
     smack
    0.73
     groundwork
    0.73
    ಸ್ಕೊ
    0.72
    POSITIVE LOGITS
     იაპ
    0.83
    燡
    0.82
     ਤੇ
    0.80
    %","
    0.80
    ين
    0.80
     რე
    0.78
    тері
    0.77
    Quem
    0.76
    )：
    0.76
    ث
    0.75
    Activations Density 0.001%

    No Known Activations