© 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. 97776
    Prev
    Next
    INDEX
    Explanations

    C: paths and copyright

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

    The neuron is primarily detecting Windows‐style absolute file paths (e.g. drive letters followed by “:\”).

    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
    })$.
    -0.78
    榭
    -0.75
    phen
    -0.75
    註
    -0.73
     pasillo
    -0.73
    ioms
    -0.73
     Rel
    -0.73
    COMB
    -0.72
     ahí
    -0.71
    الا
    -0.71
    POSITIVE LOGITS
     rosary
    0.81
    Users
    0.72
    रण
    0.69
     Travellers
    0.68
    overs
    0.66
     rosado
    0.66
     Ausbildung
    0.65
    上下
    0.65
    ั่ว
    0.64
    hem
    0.63
    Activations Density 0.034%

    No Known Activations