© 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. 10-GEMMASCOPE-RES-131K
    7. 43958
    Prev
    Next
    INDEX
    Explanations

    loops starting with 1

    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
    (),
    -2.98
    In
    -2.98
    ,”
    -2.97
    —
    -2.97
    R
    -2.97
    ↵↵
    -2.95
    <em>
    -2.92
    <i>
    -2.63
    ’,
    -2.63
    ↵
    -2.61
    POSITIVE LOGITS
    鹟
    2.50
    
    2.34
    嚒
    2.33
     مراحل
    2.30
     kimdir
    2.28
     continúas
    2.28
    ቷ
    2.28
     protocolos
    2.27
    ㌘
    2.27
     desbloquear
    2.25
    Activations Density 0.045%

    No Known Activations