© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117362
    Prev
    Next
    INDEX
    Explanations

    file paths and assignments

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

    The neuron flags code‐like or configuration tokens, especially shell commands, environment variable names, file references, and other programming/configuration keywords in code snippets.

    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
     C
    -0.75
    叭
    -0.75
    C
    -0.75
     Δη
    -0.73
    sodik
    -0.73
    providedIn
    -0.73
     فترة
    -0.73
     Neben
    -0.73
    ghana
    -0.72
    зер
    -0.71
    POSITIVE LOGITS
     "/
    3.06
     '/
    2.84
    ("/
    2.63
    ="/
    2.52
    ('/
    2.45
     ~/
    2.13
    ='/
    2.13
    "/
    2.11
     `/
    1.98
    ~/
    1.94
    Activations Density 0.112%

    No Known Activations