© 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. 8500
    Prev
    Next
    INDEX
    Explanations

    how and when

    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
    ﻊ
    -1.84
     boî
    -1.80
     Affaires
    -1.79
     estimés
    -1.75
    𓆜
    -1.73
    鱨
    -1.73
     royale
    -1.66
    )։
    -1.63
    ：……
    -1.62
     gustado
    -1.60
    POSITIVE LOGITS
     how
    1.95
     —
    1.86
    .
    1.83
    \
    1.83
     WHEN
    1.79
    </b>
    1.76
     whom
    1.67
     哪些
    1.66
     those
    1.66
     where
    1.64
    Activations Density 0.009%

    No Known Activations