© 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. 59157
    Prev
    Next
    INDEX
    Explanations

    sorting fields, trends, dialogs

    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
    </em>
    -2.83
    й
    -2.80
    </h2>
    -2.56
    Semoga
    -2.52
     \&
    -2.52
     \#
    -2.44
    \_
    -2.41
    𖧵
    -2.39
     französ
    -2.39
    ité
    -2.36
    POSITIVE LOGITS
    茈
    2.77
    
    2.44
    ⌵
    2.39
    ᠳ
    2.23
     vestidos
    2.23
    殽
    2.20
     contento
    2.19
     deseos
    2.19
    gucig
    2.17
    盞
    2.17
    Activations Density 0.001%

    No Known Activations