© 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. 40140
    Prev
    Next
    INDEX
    Explanations

    of value or importance

    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
     on
    -1.91
     are
    -1.66
     encantó
    -1.50
     at
    -1.46
     cepat
    -1.45
     vœ
    -1.44
     itinéraire
    -1.42
    𖣘
    -1.41
     Gegensatz
    -1.38
    отно
    -1.37
    POSITIVE LOGITS
     crucial
    1.70
     useful
    1.69
    </h2>
    1.68
    </h4>
    1.62
    </em>
    1.60
    很重要
    1.56
    簠
    1.53
     helpful
    1.47
     angezeigt
    1.46
     NEW
    1.45
    Activations Density 0.107%

    No Known Activations