© 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. 2259
    Prev
    Next
    INDEX
    Explanations

    get and data schemas

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

    The neuron fires on code patterns that load or fetch external data—especially calls like file_get_contents, fgetcsv, str_getcsv, and similar data‐loading routines.

    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
     KB
    -0.70
     laad
    -0.68
    bids
    -0.67
    ımı
    -0.67
     tillegg
    -0.66
    Rujuakan
    -0.66
     maal
    -0.65
    🥶
    -0.65
     errno
    -0.65
     TextField
    -0.65
    POSITIVE LOGITS
     सं
    0.70
     erklären
    0.68
     sout
    0.66
     übrigens
    0.66
    occhi
    0.65
    ale
    0.65
     nhu
    0.64
    馭
    0.64
    acz
    0.64
    gk
    0.63
    Activations Density 0.071%

    No Known Activations