© 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. 85364
    Prev
    Next
    INDEX
    Explanations

    UI elements and code components

    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
    皤
    -1.54
     limitaciones
    -1.45
    valentino
    -1.40
     inimigo
    -1.39
     reklama
    -1.38
    gettyimages
    -1.38
     população
    -1.38
     verdaderas
    -1.37
     опыта
    -1.37
     podrían
    -1.37
    POSITIVE LOGITS
     =
    1.50
    ),
    1.48
    <td>
    1.37
    type
    1.36
    th
    1.36
     will
    1.35
    五百
    1.22
    ी
    1.21
     is
    1.21
    Zapraszamy
    1.20
    Activations Density 0.433%

    No Known Activations