© 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. 128395
    Prev
    Next
    INDEX
    Explanations

    allegorical, allegiance, allegedly, alphabetically

    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
    t
    -3.13
    ar
    -2.95
    a
    -2.66
    es
    -2.59
    -
    -2.55
    i
    -2.45
    н
    -2.41
    b
    -2.34
    ть
    -2.31
    c
    -2.31
    POSITIVE LOGITS
    </h3>
    2.31
    ,“
    2.19
     begrij
    2.14
    шают
    2.14
    噲
    2.11
    </strong>
    2.11
    tienen
    2.05
    訫
    2.02
    :“
    2.02
     rempliss
    2.00
    Activations Density 0.001%

    No Known Activations