© 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. 13206
    Prev
    Next
    INDEX
    Explanations

    f-string delimiters

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

    The neuron strongly activates on URL and HTTP‐header–style tokens (e.g. “com,” “host,” “referrer,” “request,” numeric status codes), so it’s detecting parts of web‐request log entries.

    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
    "."
    0.86
    ""
    0.83
    }}"
    0.83
    '",
    0.81
    ;
    0.81
    "
    0.79
    "(
    0.76
    ":(
    0.76
    "/"
    0.76
    :"",
    0.75
    POSITIVE LOGITS
    ());
    2.33
    .);
    2.30
    );
    2.20
     []);
    2.20
     '');
    2.13
     {});
    2.09
    !);
    2.09
     "");
    2.06
    []);
    1.98
    ）；
    1.96
    Activations Density 0.011%

    No Known Activations