© 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. 10-GEMMASCOPE-RES-131K
    7. 58777
    Prev
    Next
    INDEX
    Explanations

    ages and durations

    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
     either
    -1.95
     both
    -1.60
     your
    -1.57
    那些
    -1.46
     each
    -1.43
    anız
    -1.41
    either
    -1.39
    はこちらから
    -1.38
    或
    -1.35
    mathrm
    -1.32
    POSITIVE LOGITS
    了个
    1.63
    :{
    1.61
     of
    1.45
     évé
    1.41
    ^@
    1.40
     tien
    1.39
     tercio
    1.36
     chaus
    1.36
    &
    1.36
     naman
    1.35
    Activations Density 0.327%

    No Known Activations