© 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. 38837
    Prev
    Next
    INDEX
    Explanations

    consecutive, connection, consequentialism

    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
    蹰
    -3.17
    人也
    -2.73
    ية
    -2.56
    ౖ
    -2.45
    metido
    -2.44
     無地
    -2.41
     greateſt
    -2.36
     GREG
    -2.36
    Ꮧ
    -2.36
    鉋
    -2.34
    POSITIVE LOGITS
     &
    2.95
     '
    2.89
     FOR
    2.78
     {
    2.77
     â
    2.63
    辄
    2.61
     When
    2.59
     safeguards
    2.48
     \
    2.45
    笑笑
    2.45
    Activations Density 0.007%

    No Known Activations