© 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. 128496
    Prev
    Next
    INDEX
    Explanations

    caustic, heinous, clot, createStatement, Rufus, copious, Licensed

    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
    釹
    -2.69
    [.
    -2.58
    gridy
    -2.48
     ventre
    -2.41
    头
    -2.28
     monstre
    -2.23
     Politica
    -2.20
     ventures
    -2.20
    💪
    -2.20
     estekak
    -2.19
    POSITIVE LOGITS
    ’
    3.70
    0
    3.55
    </em>
    3.06
    1
    2.73
     to
    2.58
    趼
    2.48
     is
    2.47
    ↵
    2.36
     la
    2.34
    ’,
    2.27
    Activations Density 0.036%

    No Known Activations