© 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. 26484
    Prev
    Next
    INDEX
    Explanations

    code structures like `/*` or keywords followed by `{`

    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
    outheast
    -1.30
    huur
    -1.26
     bereits
    -1.23
     their
    -1.23
    НИЙ
    -1.21
     parfüm
    -1.19
     triko
    -1.18
    ｭ
    -1.18
     koncentr
    -1.18
     fichas
    -1.17
    POSITIVE LOGITS
     is
    1.50
    ,
    1.33
    -
    1.32
     mythic
    1.03
    Instead
    1.01
    は
    0.99
    bo
    0.99
    He
    0.96
     relig
    0.95
    o
    0.93
    Activations Density 0.000%

    No Known Activations