© 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. 59232
    Prev
    Next
    INDEX
    Explanations

    true or false

    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
    ध्यम
    -1.45
     accion
    -1.38
    breite
    -1.37
    裥
    -1.33
    HMAC
    -1.28
    t
    -1.28
    鹀
    -1.28
    auté
    -1.27
     independente
    -1.27
     tao
    -1.25
    POSITIVE LOGITS
     then
    1.95
    </em>
    1.74
     they
    1.54
     by
    1.43
     Rückseite
    1.39
    年
    1.38
    </strong>
    1.38
    wości
    1.34
     bahwa
    1.33
     different
    1.32
    Activations Density 0.022%

    No Known Activations