© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35150
    Prev
    Next
    INDEX
    Explanations

    programming utilities and libraries

    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
     continues
    -1.34
    ？』
    -1.27
     noteworthy
    -1.16
     also
    -1.16
     elaborado
    -1.11
    brać
    -1.09
    ͨ
    -1.09
     numerous
    -1.09
    がありました
    -1.07
     Underwear
    -1.06
    POSITIVE LOGITS
    useNewUrlParser
    1.22
     rupiah
    1.20
     Gué
    1.10
     ￥
    1.10
    no
    1.07
    vade
    1.05
    lustre
    1.05
    ۂ
    1.04
     spree
    1.04
    too
    1.04
    Activations Density 0.041%

    No Known Activations