© 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. 48617
    Prev
    Next
    INDEX
    Explanations

    medical accuracy and technical questions

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

    programming code syntax elements like commas, brackets, and special characters in programming languages.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on programming‐language code tokens—especially module/import keywords and capitalized identifiers (type and function names).

    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
     still
    -1.38
     todavía
    -1.05
     ainda
    -1.02
     هنوز
    -0.99
     aún
    -0.94
     despite
    -0.94
     Still
    -0.91
     ancora
    -0.91
    Still
    -0.90
     noch
    -0.90
    POSITIVE LOGITS
     lás
    0.81
    ="%
    0.81
    './
    0.79
    "./
    0.79
     nimic
    0.77
    Pendidikan
    0.77
     alvo
    0.77
     byste
    0.77
     فر
    0.77
    cinco
    0.76
    Activations Density 0.004%

    No Known Activations