© 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. 47641
    Prev
    Next
    INDEX
    Explanations

    linkage map, traffic reports

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

    The neuron fires on prominent structural or metadata tokens—such as file‐header punctuation, code keywords (e.g. “static,” “proto”), section labels (e.g. “linkage”), and other document‐level markers.

    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
    scanf
    -0.88
    (\%)
    -0.81
     radikal
    -0.79
     eyebrows
    -0.77
    StreamReader
    -0.77
    сії
    -0.75
    ">"
    -0.74
    UserRepository
    -0.74
     radical
    -0.74
    glGen
    -0.74
    POSITIVE LOGITS
     écri
    0.90
     exporting
    0.80
     outlet
    0.77
     write
    0.77
     đáng
    0.77
     export
    0.77
    Préparation
    0.76
     output
    0.75
    を出
    0.75
     exportation
    0.75
    Activations Density 0.000%

    No Known Activations