© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129537
    Prev
    Next
    INDEX
    Explanations

    country codes and names

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

    Knight and color definitions

    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
     walls
    0.45
    :
    0.43
     controlled
    0.43
     two
    0.42
    rocks
    0.42
     rocks
    0.39
    IA
    0.39
    IC
    0.39
     heard
    0.39
     distributed
    0.39
    POSITIVE LOGITS
    Loksatta
    0.50
    obtenir
    0.49
    僳
    0.48
    盻
    0.48
    戽
    0.47
    तोंडा
    0.47
    ﹃
    0.47
    癀
    0.46
     moim
    0.46
    การ
    0.46
    Activations Density 0.000%

    No Known Activations