© 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. 79753
    Prev
    Next
    INDEX
    Explanations

    current time

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

    Sherbrooke Street W/West

    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
     Easier
    0.50
    ม
    0.49
    -
    0.45
    贤
    0.45
     WITHIN
    0.44
     небольшой
    0.43
    看起来
    0.43
    못
    0.43
    这款
    0.42
    不由
    0.42
    POSITIVE LOGITS
    িকাল
    0.56
    otimes
    0.54
     沖縄
    0.50
    have
    0.48
    glGet
    0.48
     しっかり
    0.47
    urow
    0.47
    下記の
    0.46
     θερ
    0.46
    ('/\
    0.45
    Activations Density 0.000%

    No Known Activations