© 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. 55843
    Prev
    Next
    INDEX
    Explanations

    software build commands

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

    The neuron fires strongly on filesystem‐style paths and include directives—e.g. the slashes, “#”, and “.h” tokens that appear in code 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
    flow
    -0.79
     Flows
    -0.74
    Flow
    -0.73
    flows
    -0.71
     extinguished
    -0.69
    Bir
    -0.68
     bandit
    -0.66
     Flow
    -0.66
    ape
    -0.66
    alima
    -0.65
    POSITIVE LOGITS
    funko
    0.76
    kimono
    0.76
    gilet
    0.75
    stray
    0.75
    figurine
    0.74
    sculpture
    0.73
    grunge
    0.71
    emporio
    0.71
    assorted
    0.70
    Deer
    0.70
    Activations Density 0.083%

    No Known Activations