© 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. 84020
    Prev
    Next
    INDEX
    Explanations

    items priced

    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
    雰囲
    -2.34
     It
    -2.23
     impressão
    -2.20
    5
    -2.17
     concernant
    -2.16
     titulada
    -2.13
    1
    -2.11
    ”:
    -2.08
     basado
    -2.06
     sämtliche
    -2.05
    POSITIVE LOGITS
    k
    2.53
    衚
    2.23
    al
    2.16
     oktober
    2.14
    ykjav
    2.08
     odeur
    2.08
    E
    2.08
     heeft
    2.06
    ",
    2.05
    B
    1.98
    Activations Density 0.005%

    No Known Activations