© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10625
    Prev
    Next
    INDEX
    Explanations

    walking and variations thereof

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

    walking and hiking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ㊙
    0.58
    mysql
    0.43
    殲
    0.43
    DBMS
    0.42
     MySQL
    0.42
    governmental
    0.42
    ushchev
    0.42
     எம்
    0.42
    CIA
    0.41
    欉
    0.41
    POSITIVE LOGITS
     walking
    1.73
     Walking
    1.66
    Walking
    1.58
    walking
    1.54
    步行
    1.47
     walk
    1.46
     walked
    1.46
    🚶
    1.46
    歩
    1.45
     walks
    1.43
    Activations Density 0.215%

    No Known Activations