© 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. 34-GEMMASCOPE-RES-131K
    7. 47805
    Prev
    Next
    INDEX
    Explanations

    license and copyright notices

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

    The neuron fires most strongly on long, formal words in code‐comment headers and documentation (e.g. “Application,” “part,” “information,” “documentation,” “sniffer,” “implied,” “damages”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    晞
    -0.79
     Pá
    -0.78
    ńskiej
    -0.75
    timeouts
    -0.75
    toolBar
    -0.75
    mbolos
    -0.75
    ázs
    -0.74
    Kaiser
    -0.73
    莴
    -0.73
     bọc
    -0.73
    POSITIVE LOGITS
     заяв
    0.87
     Tracker
    0.83
    ರೆ
    0.82
     lieb
    0.80
    perature
    0.77
     Magnet
    0.76
     tutu
    0.75
    ntry
    0.74
     bait
    0.73
     ぼ
    0.73
    Activations Density 0.001%

    No Known Activations