© 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. 102701
    Prev
    Next
    INDEX
    Explanations

    official news and disclaimers

    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
    Furthermore
    -1.30
     rū
    -1.30
    diven
    -1.23
     abenço
    -1.21
     Также
    -1.20
     Furthermore
    -1.19
     lagerfeld
    -1.19
     設置
    -1.16
     incred
    -1.15
    OfSize
    -1.13
    POSITIVE LOGITS
    ised
    1.32
     there
    1.23
     still
    1.22
     машине
    1.17
     name
    1.16
     kics
    1.16
     includes
    1.14
    نت
    1.13
    rozco
    1.13
     &
    1.10
    Activations Density 0.164%

    No Known Activations