© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12027
    Prev
    Next
    INDEX
    Explanations

    discretionary review

    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
     ſever
    -2.45
    薅
    -2.44
    嘥
    -2.39
    颪
    -2.38
     Inſ
    -2.34
    
    -2.34
    跩
    -2.33
    ндарт
    -2.33
    奩
    -2.33
    訐
    -2.30
    POSITIVE LOGITS
    "
    3.16
    ).
    3.02
    '
    2.59
    0
    2.56
     (
    2.42
    ),
    2.41
    ↵↵
    2.39
    w
    2.36
    ;
    2.34
     is
    2.33
    Activations Density 0.002%

    No Known Activations