© 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. 27421
    Prev
    Next
    INDEX
    Explanations

    This is a capability

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

    security and access

    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
    年度
    0.53
     tanda
    0.47
    এদিকে
    0.47
     |
    0.46
     এদিকে
    0.44
     촬영
    0.44
    🐪
    0.44
    かう
    0.44
     ${
    0.44
    たくさん
    0.44
    POSITIVE LOGITS
     gyakor
    0.47
    ธุ์
    0.46
     některé
    0.44
    HTree
    0.42
    GTBase
    0.42
    рони
    0.42
     كيف
    0.41
     dwells
    0.41
     ressemble
    0.41
    Def
    0.40
    Activations Density 0.000%

    No Known Activations