© 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. 44275
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with delimiters

    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
     with
    -2.02
    end
    -1.90
     out
    -1.88
    O
    -1.85
     For
    -1.82
    M
    -1.77
    R
    -1.75
     in
    -1.75
    (
    -1.73
    änemark
    -1.73
    POSITIVE LOGITS
     becas
    2.14
    呖
    2.13
    也将
    2.11
    時も
    2.11
    ANIEL
    2.06
     Répondre
    2.03
    他的
    2.03
    歺
    2.00
     estekak
    2.00
    izing
    1.98
    Activations Density 0.019%

    No Known Activations