© 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. 21042
    Prev
    Next
    INDEX
    Explanations

    in, on, at

    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
    ógicas
    -1.40
     )
    -1.39
    </em>
    -1.39
     on
    -1.38
    Šaltiniai
    -1.29
     where
    -1.28
    long
    -1.28
    @"
    -1.27
     and
    -1.27
     in
    -1.27
    POSITIVE LOGITS
    spanning
    1.44
    Santé
    1.44
    alamu
    1.41
    嘻嘻
    1.41
    placing
    1.40
     mated
    1.39
     tampaknya
    1.38
    accessoires
    1.38
     sogni
    1.36
    για
    1.35
    Activations Density 0.145%

    No Known Activations