© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1534
    Prev
    Next
    INDEX
    Explanations

    app = or app

    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
     of
    -1.88
    şme
    -1.67
    ława
    -1.59
     Mereka
    -1.57
     اینکه
    -1.55
    ほしい
    -1.55
    PreInfinity
    -1.55
     dàng
    -1.54
    𖧵
    -1.52
    YNAMICS
    -1.51
    POSITIVE LOGITS
    .
    1.98
    If
    1.69
    Most
    1.63
    One
    1.60
    Two
    1.60
    What
    1.58
     could
    1.55
    There
    1.55
    Perhaps
    1.55
     one
    1.53
    Activations Density 0.004%

    No Known Activations