© 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. 22-GEMMASCOPE-RES-131K
    7. 128217
    Prev
    Next
    INDEX
    Explanations

    linting and code analysis rules

    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_22/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
     چربی
    -1.20
     people
    -1.19
     with
    -1.16
    Despite
    -1.14
     Despite
    -1.12
     procedures
    -1.08
     strange
    -1.05
     six
    -1.05
     extraordinary
    -1.04
     five
    -1.02
    POSITIVE LOGITS
     prévention
    1.23
     проверя
    1.20
     targeted
    1.16
    targeted
    1.16
     against
    1.14
     '-':
    1.06
    análisis
    1.06
    makeConstraints
    1.06
     rilev
    1.05
    ſa
    1.05
    Activations Density 0.088%

    No Known Activations