© 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. 85400
    Prev
    Next
    INDEX
    Explanations

    Electromigration, affecting

    np_acts-logits-general · gemini-2.5-flash-lite

    the arrow operator (`->`) used to access structure members in C/C++ code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    us
    -1.67
    有效的
    -1.59
    к
    -1.55
    怎么可能
    -1.51
    rativa
    -1.48
    //
    -1.47
    mallera
    -1.46
    0
    -1.46
    ts
    -1.45
     singled
    -1.45
    POSITIVE LOGITS
    
    2.00
    \
    1.93
    yyj
    1.71
     VOUS
    1.70
     diário
    1.69
    疒
    1.62
    缛
    1.60
     IBRARY
    1.60
    」,
    1.59
     オレンジ
    1.57
    Activations Density 0.002%

    No Known Activations