© 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. 45224
    Prev
    Next
    INDEX
    Explanations

    javax. followed by code

    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
     “
    -2.53
    ”,
    -2.33
    ’,
    -2.08
    </em>
    -2.06
     (“
    -1.97
    ↵
    -1.95
     divertidas
    -1.88
    </h4>
    -1.83
    ,’
    -1.82
    sterreich
    -1.80
    POSITIVE LOGITS
     alugar
    1.98
     '
    1.95
    eryllium
    1.94
    5
    1.93
    ⾦
    1.87
    身边的
    1.86
    ;"
    1.82
    还有什么
    1.75
     Imágenes
    1.69
    鱚
    1.69
    Activations Density 0.000%

    No Known Activations