© 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. 22-GEMMASCOPE-RES-131K
    7. 34152
    Prev
    Next
    INDEX
    Explanations

    electrically connected

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

    The neuron strongly activates on formal, technical or scientific vocabulary—words that occur in patent‐style or academic descriptions (e.g. “providing,” “equals,” “polytope,” “coordinate,” “environment,” “addition”).

    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
     automatiquement
    -1.13
     nástro
    -1.10
     Guinée
    -1.09
    gesi
    -1.08
     způ
    -1.07
    ebbe
    -1.05
     //$
    -1.02
     anhand
    -1.02
     thermique
    -1.02
    
    -1.02
    POSITIVE LOGITS
     sekitarnya
    1.02
     Furthermore
    1.02
    What
    0.97
     would
    0.95
    Fifteen
    0.93
     Moreover
    0.92
    there
    0.91
    When
    0.91
    This
    0.90
     However
    0.90
    Activations Density 0.077%

    No Known Activations