© 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. 11394
    Prev
    Next
    INDEX
    Explanations

    outcomes of tests and competitions

    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
     only
    -1.50
     ONLY
    -1.33
     not
    -1.33
     for
    -1.30
     květ
    -1.23
     also
    -1.20
    ierten
    -1.17
    visiae
    -1.17
    具体
    -1.16
     září
    -1.15
    POSITIVE LOGITS
     by
    1.23
    unst
    1.16
     gana
    1.10
     Сегодня
    1.08
    *>(
    1.08
    riet
    1.06
     comparison
    1.05
     tegens
    1.03
     distinguishing
    1.03
    OHN
    1.02
    Activations Density 0.065%

    No Known Activations