© 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. 408
    Prev
    Next
    INDEX
    Explanations

    initial caps followed by keyword

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

    This neuron activates on tokens that are uppercase identifiers or macros (e.g., all-caps names with underscores and numbers).

    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
     in
    -1.97
     one
    -1.93
     all
    -1.67
     more
    -1.57
     like
    -1.44
     on
    -1.44
     this
    -1.42
     just
    -1.39
     what
    -1.38
     every
    -1.30
    POSITIVE LOGITS
     levering
    1.38
    蟊
    1.34
     EIGHT
    1.31
    镲
    1.30
     améliorer
    1.30
    
    1.30
    趿
    1.29
     glistening
    1.27
     delectable
    1.26
     devast
    1.25
    Activations Density 0.010%

    No Known Activations