© 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. 107980
    Prev
    Next
    INDEX
    Explanations

    legal, property, quantities, details

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

    security, math, and art concepts

    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
    Negative Logits
    asis
    0.55
     beings
    0.53
    forecast
    0.51
    isub
    0.50
    ysis
    0.49
     swivel
    0.49
    ist
    0.48
    ^{*}
    0.47
    isopropyl
    0.47
     forecast
    0.47
    POSITIVE LOGITS
     Reichs
    0.47
     రాజ
    0.46
     Хи
    0.45
    ufieurs
    0.45
     Ж
    0.44
    ૃહ
    0.44
    MyHomePage
    0.43
    теше
    0.43
    DET
    0.42
     Ratch
    0.42
    Activations Density 0.000%

    No Known Activations