© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34392
    Prev
    Next
    INDEX
    Explanations

    university names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ~
    -1.48
     &
    -1.38
    凄く
    -1.38
    -
    -1.38
    &
    -1.36
    _
    -1.32
     of
    -1.31
     a
    -1.25
    為に
    -1.25
    {
    -1.23
    POSITIVE LOGITS
    子を
    1.34
    plätze
    1.33
    垢
    1.31
     Teknologi
    1.30
    ꈊ
    1.28
    ENER
    1.27
    tembro
    1.27
    دانلود
    1.25
    alties
    1.24
    haviours
    1.24
    Activations Density 0.034%

    No Known Activations