© 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. 112554
    Prev
    Next
    INDEX
    Explanations

    years, dates

    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
    if
    -1.48
     if
    -1.48
     mengatasi
    -1.43
     questo
    -1.38
     primero
    -1.31
    ्स
    -1.30
     awalnya
    -1.27
     these
    -1.27
     from
    -1.27
    山的
    -1.24
    POSITIVE LOGITS
    .
    1.41
     year
    1.38
     опыта
    1.37
    Approximately
    1.34
     gratuita
    1.27
     Approximately
    1.27
     Dokumente
    1.25
     моего
    1.25
     onwards
    1.23
    '
    1.23
    Activations Density 0.235%

    No Known Activations