© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8486
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by large floating‐point numeric tokens (e.g. metadata values like timestamps or file‐size numbers).

    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_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
    /,
    0.75
    $/,
    0.75
    ;',
    0.74
     />,
    0.69
    '],
    0.68
     фильма
    0.68
    VARIANT
    0.67
    +',
    0.67
    $',
    0.67
    '$,
    0.67
    POSITIVE LOGITS
     இதை
    0.78
    しかない
    0.77
     pyautogui
    0.77
     معاملہ
    0.76
    不得
    0.74
     उम्मीद
    0.71
    ന്ത
    0.71
    ياه
    0.71
     hydroelectric
    0.70
    তে
    0.70
    Activations Density 0.000%

    No Known Activations