© 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. 14972
    Prev
    Next
    INDEX
    Explanations

    warranted, due, order, time

    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
    s
    -1.91
    ’
    -1.75
    -
    -1.31
    <h3>
    -1.21
     ところ
    -1.20
    pI
    -1.17
    witter
    -1.14
     RECENT
    -1.11
     previously
    -1.09
     Như
    -1.09
    POSITIVE LOGITS
    覷
    1.58
     a
    1.50
    haped
    1.32
    
    1.30
     beslu
    1.28
    нії
    1.27
     内衣
    1.27
    </h4>
    1.26
     veía
    1.25
    Etter
    1.25
    Activations Density 0.024%

    No Known Activations