© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5749
    Prev
    Next
    INDEX
    Explanations

    code definitions and comments

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

    The neuron activates on numeric tokens (sequences of digits and numbers, including integers, floats, and pixel‐resolution figures).

    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
    )&&
    0.70
    ");*/
    0.65
    )");
    0.63
     पेशे
    0.61
    );*/
    0.58
    ?");
    0.57
    ]?.
    0.57
    ).[
    0.57
    ]/*
    0.55
    )?.
    0.54
    POSITIVE LOGITS
    Python
    1.00
     //
    0.94
     python
    0.92
    //
    0.91
    python
    0.91
     Python
    0.88
    (**
    0.88
    Py
    0.86
     tkinter
    0.86
     Py
    0.83
    Activations Density 0.000%

    No Known Activations