© 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. 22-GEMMASCOPE-RES-131K
    7. 129250
    Prev
    Next
    INDEX
    Explanations

    section titles, enumeration

    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
     וכן
    -1.13
     می‌ده
    -1.00
    jangkau
    -0.98
     voetballer
    -0.96
     работу
    -0.94
    athione
    -0.94
    ttää
    -0.93
     tą
    -0.93
    undet
    -0.92
     last
    -0.92
    POSITIVE LOGITS
    B
    0.97
     seguida
    0.95
     quarries
    0.93
    %">
    0.92
    TICKETS
    0.91
    Ooooo
    0.91
    }}}{
    0.91
    та
    0.90
     ceremonia
    0.90
    ди
    0.89
    Activations Density 0.031%

    No Known Activations