© 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. 101024
    Prev
    Next
    INDEX
    Explanations

    of the

    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>
    -2.83
    Those
    -2.42
    These
    -2.30
    There
    -2.25
    ",
    -2.22
     difficult
    -2.20
     incredible
    -2.16
     remarkable
    -2.14
     very
    -2.13
     more
    -2.11
    POSITIVE LOGITS
     the
    5.13
     pérd
    2.63
    皤
    2.39
    滏
    2.39
     verhind
    2.33
    itization
    2.27
    ଃ
    2.25
     avocat
    2.22
     evangé
    2.20
    vereignty
    2.19
    Activations Density 0.765%

    No Known Activations