© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33234
    Prev
    Next
    INDEX
    Explanations

    an or Q

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

    The neuron fires on numeric coordinate tokens in vector‐graphic path data (e.g. numbers in an SVG “d”/path attribute).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    を決
    -0.90
    ço
    -0.86
    ویت
    -0.85
     матч
    -0.85
    ,-.
    -0.85
    TURE
    -0.84
    ড়
    -0.83
     stroj
    -0.81
    дли
    -0.78
    未来
    -0.78
    POSITIVE LOGITS
    ibatkan
    0.94
     переход
    0.86
    そのような
    0.85
     شکر
    0.85
     intervening
    0.84
    遊ぶ
    0.83
     sequential
    0.82
     P
    0.81
     ".";
    0.81
     intermediary
    0.79
    Activations Density 0.000%

    No Known Activations