© 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. 33761
    Prev
    Next
    INDEX
    Explanations

    code delimiters including } and ;

    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
    घ
    -0.99
    Ď
    -0.94
    но
    -0.91
    )_{
    -0.89
     sánh
    -0.88
    
    -0.88
     spender
    -0.88
    ഫ
    -0.86
    بة
    -0.85
    了一眼
    -0.85
    POSITIVE LOGITS
    Bologna
    0.92
    יפור
    0.83
     seçenek
    0.78
    מונות
    0.77
     to
    0.77
     olmaz
    0.76
     очередь
    0.75
     łyż
    0.75
    Chandigarh
    0.75
     linguri
    0.75
    Activations Density 0.005%

    No Known Activations