© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82777
    Prev
    Next
    INDEX
    Explanations

    waveform image color

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

    This neuron detects filesystem path components (slashes and the directory or filename tokens that appear in file paths).

    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
    èt
    -0.93
    niosek
    -0.83
    īg
    -0.75
    ējās
    -0.73
    雑誌
    -0.73
     pidiendo
    -0.73
    ībā
    -0.72
    ་བ
    -0.72
    timb
    -0.72
    ✿
    -0.71
    POSITIVE LOGITS
     PPM
    1.05
    ppm
    1.03
     ppm
    1.01
    clientHeight
    0.96
    tery
    0.82
    HEADER
    0.81
     canvas
    0.81
    {(\
    0.78
    Framebuffer
    0.78
     header
    0.74
    Activations Density 0.006%

    No Known Activations