© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83989
    Prev
    Next
    INDEX
    Explanations

    official bodies and actions

    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
     citroen
    -1.40
     their
    -1.36
     hjemmeside
    -1.34
     può
    -1.27
     globales
    -1.25
     två
    -1.24
     barnet
    -1.24
     bianca
    -1.23
    “……”
    -1.23
     装饰
    -1.23
    POSITIVE LOGITS
    Nj
    1.24
     nacer
    1.23
    omaly
    1.23
     battle
    1.20
     best
    1.20
     especí
    1.18
    ından
    1.16
    sbereich
    1.16
     elevar
    1.16
     quede
    1.16
    Activations Density 0.037%

    No Known Activations