© 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. 25763
    Prev
    Next
    INDEX
    Explanations

    Cardiotoxicity and NEW VIDEO

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

    SVG path data or vector drawing instructions in code files.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on numeric tokens (digit sequences), especially coordinate numbers in the SVG/XML path data.

    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
     decreased
    -0.95
    ométrique
    -0.94
     measurements
    -0.91
    岁的
    -0.88
     timbul
    -0.84
     mittler
    -0.83
     colheres
    -0.83
    لينا
    -0.82
    arthur
    -0.82
     increased
    -0.82
    POSITIVE LOGITS
    襟
    0.93
     grandiose
    0.89
     lauded
    0.82
     CAND
    0.81
     FIF
    0.78
     FIRST
    0.77
    分页
    0.77
    owan
    0.76
    RECT
    0.76
     tsl
    0.76
    Activations Density 0.006%

    No Known Activations