© 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. 22-GEMMASCOPE-RES-131K
    7. 36012
    Prev
    Next
    INDEX
    Explanations

    closed eyes

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

    The neuron fires on open‐class content words (nouns, verbs, adjectives, pronouns, etc.) and ignores function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ^{
    -0.98
    section
    -0.98
     during
    -0.96
    hops
    -0.95
    hms
    -0.93
    imetry
    -0.88
    imedes
    -0.87
     vitales
    -0.87
     températures
    -0.87
    ORS
    -0.87
    POSITIVE LOGITS
    РЫ
    0.96
    何时
    0.92
     demora
    0.90
     didn
    0.90
    课堂
    0.90
    듭
    0.90
    遲
    0.88
     skog
    0.87
    やってる
    0.86
    ogener
    0.86
    Activations Density 0.018%

    No Known Activations