© 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. 76681
    Prev
    Next
    INDEX
    Explanations

    code and file paths

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

    The neuron fires on tokens that look like file‐system path components (e.g. “C://windows/System32/…”).

    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
    /*---
    -0.72
     drowned
    -0.72
    прият
    -0.70
    Plays
    -0.69
     Crosse
    -0.68
    pozorn
    -0.67
    ственной
    -0.66
    AMBI
    -0.66
    MouseEvent
    -0.65
     Batista
    -0.65
    POSITIVE LOGITS
    pdb
    0.80
    υναι
    0.68
    谙
    0.66
    ELAND
    0.65
     illuminating
    0.64
     stehen
    0.63
    HH
    0.63
    voegen
    0.63
     Georgie
    0.63
    olation
    0.62
    Activations Density 0.054%

    No Known Activations