© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61277
    Prev
    Next
    INDEX
    Explanations

    in order to, have to

    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_10/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
    s
    -1.38
    tungen
    -1.35
    nosi
    -1.34
    Tapi
    -1.33
    푘
    -1.31
     スーツ
    -1.25
     NICK
    -1.23
     レザー
    -1.23
     celles
    -1.23
     også
    -1.22
    POSITIVE LOGITS
    神情
    1.80
     it
    1.73
     There
    1.70
     there
    1.67
    There
    1.66
    there
    1.48
    2
    1.47
     they
    1.45
     Aufwand
    1.45
     I
    1.44
    Activations Density 0.050%

    No Known Activations