© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108061
    Prev
    Next
    INDEX
    Explanations

    data conversion

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

    The neuron is primarily detecting numeric tokens (digits and number literals) in code or text.

    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
     strlen
    -0.69
    icha
    -0.68
     Formel
    -0.68
    tego
    -0.67
    melidir
    -0.67
    quartered
    -0.66
    lija
    -0.66
    nyk
    -0.66
    imwrite
    -0.66
    țin
    -0.65
    POSITIVE LOGITS
     dto
    0.98
    dto
    0.94
     Conversion
    0.78
     DTO
    0.77
    皈
    0.75
     conversions
    0.74
     希
    0.74
     conversion
    0.74
     roleId
    0.73
    Conversion
    0.72
    Activations Density 0.062%

    No Known Activations