© 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. 64681
    Prev
    Next
    INDEX
    Explanations

    parentheses and code comments

    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
     !!!!
    -1.50
    !!!!!!
    -1.45
     jeudi
    -1.28
     huiles
    -1.27
    thof
    -1.27
     жк
    -1.23
    を変更
    -1.23
    !!!!!!!
    -1.22
     déchets
    -1.22
     !!!!!
    -1.21
    POSITIVE LOGITS
     how
    1.30
    申し上げます
    1.20
     seems
    1.12
     any
    1.10
     as
    1.07
     burgeoning
    1.07
     perhaps
    1.05
     admiring
    1.05
     هو
    1.02
     unusually
    1.02
    Activations Density 0.004%

    No Known Activations