© 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. 57749
    Prev
    Next
    INDEX
    Explanations

    reading texts that involve "More"

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

    This neuron fires on tokens used in auto-generated API documentation and Markdown/YAML metadata (e.g., “API,” “Doc,” “umenter,” “Publisher Options,” file extensions, front‐matter keys).

    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
    ovina
    -0.88
    detach
    -0.84
    ことはありません
    -0.82
    eniendo
    -0.81
     chịu
    -0.79
     lediglich
    -0.79
     Wortes
    -0.78
    ()));
    -0.76
    艺人
    -0.75
     sản
    -0.73
    POSITIVE LOGITS
    <h1>
    1.07
    Rend
    0.81
     Cartagena
    0.77
    ைகள்
    0.77
    แก้
    0.76
     actitud
    0.75
    وقت
    0.75
     ♦
    0.73
    technologies
    0.73
    [!
    0.72
    Activations Density 0.030%

    No Known Activations