© 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. 39464
    Prev
    Next
    INDEX
    Explanations

    other

    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
    
    -2.28
    齮
    -2.22
    苼
    -2.22
    臜
    -2.22
    
    -2.16
     viste
    -2.08
     entram
    -2.06
    푆
    -2.03
     taki
    -2.02
     vijf
    -2.02
    POSITIVE LOGITS
    羂
    2.88
    та
    2.69
    The
    2.59
    worldly
    2.59
     multitude
    2.44
     There
    2.38
     bestimmten
    2.38
     unangemess
    2.33
     berserk
    2.33
    后感
    2.31
    Activations Density 0.016%

    No Known Activations