© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34609
    Prev
    Next
    INDEX
    Explanations

    rights reserved

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

    The neuron fires on relatively uncommon, content-heavy tokens—often legal or technical keywords (e.g. “rights,” “reserved,” “haven’t”) that stand out from boilerplate text.

    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
    нинград
    -0.79
    bonjour
    -0.75
    мите
    -0.72
    Helmet
    -0.72
    ellschaft
    -0.72
    /[
    -0.71
     Yates
    -0.71
    behör
    -0.70
     Sinter
    -0.70
    Asm
    -0.69
    POSITIVE LOGITS
    unkel
    0.71
    nean
    0.66
    osum
    0.66
    pett
    0.66
    馳走
    0.66
    MotionEvent
    0.66
     ਦ
    0.66
     jednak
    0.65
     бор
    0.65
    jective
    0.65
    Activations Density 0.059%

    No Known Activations