© 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. 33223
    Prev
    Next
    INDEX
    Explanations

    section headers and specific nouns

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

    The neuron fires on copular “is a” (and similar “This is a,” “It is a,” etc.) constructions introducing definitions or descriptions.

    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
    esch
    -0.92
    ="[
    -0.90
     zrobić
    -0.89
    ucha
    -0.89
    volezza
    -0.88
    ⁎
    -0.85
    Leather
    -0.84
    昴
    -0.82
    aol
    -0.81
    
    -0.81
    POSITIVE LOGITS
     straight
    1.11
     sleeveless
    1.06
     regular
    1.05
     open
    0.97
     long
    0.95
     Slee
    0.94
     closed
    0.93
     full
    0.93
     fitted
    0.93
     slim
    0.90
    Activations Density 0.019%

    No Known Activations