© 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. 22-GEMMASCOPE-RES-131K
    7. 13397
    Prev
    Next
    INDEX
    Explanations

    padding and css properties

    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_22/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
     This
    -2.50
    垰
    -2.31
    盌
    -2.30
    籏
    -2.19
    ‘
    -2.09
    
    -2.09
    喼
    -2.02
     没有
    -2.00
    蹋
    -1.98
     bronzo
    -1.93
    POSITIVE LOGITS
    虓
    2.55
    薆
    2.42
    Ꮸ
    2.38
    ᯾
    2.33
    鱨
    2.28
    
    2.20
    ixante
    2.17
    蚡
    2.16
    
    2.13
    ?
    2.11
    Activations Density 0.002%

    No Known Activations