© 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. 66459
    Prev
    Next
    INDEX
    Explanations

    default value assignment

    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
    轳
    -1.51
    肫
    -1.45
    дельник
    -1.41
    GraphicsUnit
    -1.40
    erráneo
    -1.38
    ArgsConstructor
    -1.38
    StoryboardSegue
    -1.38
    IDEOGRAPH
    -1.35
    HostException
    -1.35
    >("
    -1.34
    POSITIVE LOGITS
     this
    1.76
     on
    1.34
     it
    1.33
     to
    1.30
     for
    1.27
     attuale
    1.27
     after
    1.23
     just
    1.19
     but
    1.18
    as
    1.17
    Activations Density 0.012%

    No Known Activations