© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8549
    Prev
    Next
    INDEX
    Explanations

    `Program Files` clauses `Const` `string` `Everyday`

    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
     qualquer
    -1.38
     любой
    -1.36
     cualquier
    -1.36
    стики
    -1.36
     любого
    -1.30
     serão
    -1.30
    epiece
    -1.30
    쫀
    -1.27
     เรา
    -1.26
     akces
    -1.26
    POSITIVE LOGITS
     from
    2.19
     such
    1.69
     with
    1.63
     viņ
    1.45
     of
    1.41
     it
    1.38
     for
    1.38
    The
    1.37
     šo
    1.36
     not
    1.35
    Activations Density 0.293%

    No Known Activations