© 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. 10-GEMMASCOPE-RES-131K
    7. 101230
    Prev
    Next
    INDEX
    Explanations

    file paths and directories

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

    file paths and directory structures in technical/programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is detecting version‐control and build cache directory names (e.g. “CVS,” “.svn,” “autom4te.cache,” etc.) in file path listings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     in
    -1.35
     compared
    -1.28
     and
    -1.28
     for
    -1.13
     especially
    -1.13
    VELAND
    -1.13
    }$,
    -1.12
     }}(\
    -1.12
    ためには
    -1.11
    ђ
    -1.11
    POSITIVE LOGITS
    Примі
    1.17
     not
    1.17
     После
    1.15
    Олег
    1.14
    了些
    1.14
    _
    1.13
    了一会儿
    1.10
     zelo
    1.10
    了许多
    1.07
    证据
    1.05
    Activations Density 0.105%

    No Known Activations