© 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. 66061
    Prev
    Next
    INDEX
    Explanations

    special characters or section titles

    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
     your
    -1.28
    ervations
    -1.27
    ...@
    -1.23
    IOR
    -1.20
    ))[
    -1.20
    筠
    -1.20
    WriteHeader
    -1.15
    JW
    -1.15
    OTTEN
    -1.14
     to
    -1.13
    POSITIVE LOGITS
    Embal
    1.18
    呦
    1.17
    Gön
    1.16
    Recept
    1.15
    もあって
    1.09
    Rena
    1.06
    抹茶
    1.03
    战斗力
    1.02
     pectoral
    1.02
    Conse
    1.02
    Activations Density 0.000%

    No Known Activations