© 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. 81668
    Prev
    Next
    INDEX
    Explanations

    windows file paths

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

    This neuron detects tokens belonging to absolute Windows file paths (e.g. drive letters like “C:\” and backslashes in 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
    <bos>
    -0.83
    gráfico
    -0.81
    groupid
    -0.75
     thở
    -0.75
    *)((
    -0.74
    Neden
    -0.74
    }$-
    -0.70
    ProductService
    -0.69
     tetap
    -0.67
     могу
    -0.67
    POSITIVE LOGITS
    Users
    2.00
     Users
    1.50
     users
    1.45
    users
    1.05
    Temp
    1.02
    USERS
    1.01
    Program
    1.01
    inet
    0.98
     użytk
    0.96
     Dokumente
    0.93
    Activations Density 0.008%

    No Known Activations