© 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. 15261
    Prev
    Next
    INDEX
    Explanations

    impart or confer a characteristic

    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
     knows
    -1.46
     know
    -1.31
     Then
    -1.23
    取り組み
    -1.18
    りする
    -1.16
     demonstrated
    -1.16
     boletín
    -1.15
     comenzaron
    -1.14
     Gubernur
    -1.13
     known
    -1.13
    POSITIVE LOGITS
     réalisateur
    1.42
     refugi
    1.36
    皤
    1.32
     dün
    1.30
    Cutting
    1.28
     polé
    1.27
    ய்ய
    1.27
     avoir
    1.27
     obce
    1.26
     vieille
    1.23
    Activations Density 0.029%

    No Known Activations