© 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. 9278
    Prev
    Next
    INDEX
    Explanations

    general

    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
    </h2>
    -1.64
    </h5>
    -1.60
     our
    -1.52
    我们的
    -1.25
    ")
    -1.21
    '];
    -1.20
    ()];
    -1.18
    utek
    -1.16
    }];
    -1.16
    лару
    -1.16
    POSITIVE LOGITS
    most
    1.65
    Most
    1.43
    About
    1.34
    However
    1.32
    while
    1.30
    Did
    1.27
    There
    1.26
    first
    1.25
    about
    1.25
    General
    1.20
    Activations Density 0.076%

    No Known Activations