© 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. 15088
    Prev
    Next
    INDEX
    Explanations

    loop increment (j++)

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

    The neuron is highly sensitive to integer literals in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     anything
    -1.04
    を
    -0.87
     Has
    -0.87
    )();
    -0.85
     Filling
    -0.85
     Ion
    -0.83
    ssens
    -0.83
     Of
    -0.82
     to
    -0.82
    داء
    -0.81
    POSITIVE LOGITS
     we
    0.93
    ícias
    0.93
    词汇
    0.92
    тура
    0.91
    ࣪
    0.91
    쏙
    0.90
    碚
    0.90
    我們
    0.90
     meninos
    0.90
    ,
    0.89
    Activations Density 0.001%

    No Known Activations