© 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. 71758
    Prev
    Next
    INDEX
    Explanations

    function calls

    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
    !—
    -1.41
    ;—
    -1.31
    geblich
    -1.22
    ORPG
    -1.16
     emosi
    -1.12
    ……….
    -1.11
     lastly
    -1.10
     tindak
    -1.10
     resides
    -1.09
     ajoute
    -1.09
    POSITIVE LOGITS
     one
    1.47
     -
    1.43
     to
    1.34
     its
    1.23
    谕
    1.22
     />
    1.20
     尔
    1.19
     {
    1.18
     />
    1.18
     一九
    1.17
    Activations Density 0.032%

    No Known Activations