© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 13049
    Prev
    Next
    INDEX
    Explanations

    code syntax

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

    The neuron fires on numeric tokens and number-related placeholders or format specifiers (e.g. digits, `%INTEGER`, `%DATE`, `%STRING`, and `%(t:…)`‐style format codes).

    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
    Arctic
    0.67
    ,}
    0.59
    얘
    0.59
    {}\
    0.59
    《
    0.59
    ','')
    0.58
    ===========
    0.57
    Pretty
    0.56
    Legends
    0.56
    Fuj
    0.56
    POSITIVE LOGITS
    )";
    0.83
    )",
    0.79
    }";
    0.79
    )"
    0.72
    ]",
    0.69
     Esq
    0.69
     grams
    0.68
     kDa
    0.67
    ]";
    0.66
    ]".
    0.65
    Activations Density 0.025%

    No Known Activations