© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74546
    Prev
    Next
    INDEX
    Explanations

    2 followed by numbers

    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
    我先
    -2.28
    啬
    -2.28
    いただいて
    -2.23
     či
    -2.13
     is
    -2.11
     I
    -2.08
     vienen
    -2.00
     své
    -2.00
     quieren
    -1.95
    嬬
    -1.94
    POSITIVE LOGITS
    硨
    2.80
     présidenti
    2.78
     hunde
    2.53
    芣
    2.53
     书法
    2.53
     fald
    2.52
     dipinto
    2.52
    They
    2.52
     Politica
    2.50
     umbro
    2.50
    Activations Density 0.011%

    No Known Activations