© 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. 99244
    Prev
    Next
    INDEX
    Explanations

    keyboard and mouse events

    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
    i
    -3.03
    y
    -2.91
    your
    -2.64
    an
    -2.63
    </h3>
    -2.56
    which
    -2.50
    Maybe
    -2.42
    Being
    -2.42
    Quite
    -2.41
    Now
    -2.33
    POSITIVE LOGITS
    鹛
    2.55
     enfati
    2.47
     แต่
    2.47
     pretende
    2.22
     únicamente
    2.19
    をつける
    2.16
     rámci
    2.14
     brinda
    2.14
     solamente
    2.13
     entièrement
    2.11
    Activations Density 0.002%

    No Known Activations