© 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. 6218
    Prev
    Next
    INDEX
    Explanations

    code closing tags"},">

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

    The neuron fires strongly on URL strings and HTML tag attributes (e.g. “http”, domain names, attribute names/values).

    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
    /')
    0.66
     />';
    0.65
    '})
    0.60
    ',)
    0.60
    /');
    0.57
     ');
    0.57
    /',
    0.56
     ')
    0.56
     *,
    0.56
     '),
    0.54
    POSITIVE LOGITS
    "><
    1.87
    ">
    1.75
    ">$
    1.48
    ">(
    1.48
    ()">
    1.44
    ">-
    1.43
    ">&
    1.40
    }">
    1.35
    ]">
    1.34
    ">[
    1.33
    Activations Density 0.016%

    No Known Activations