© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38643
    Prev
    Next
    INDEX
    Explanations

    innovative approaches, techniques, and fields

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

    The neuron selectively activates on the adjective “innovative” (and its close morphological variants) in 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_10/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
    2
    -2.70
    0
    -2.06
    3
    -1.98
    说完
    -1.95
    お客
    -1.91
    colgante
    -1.88
    8
    -1.84
     Wettbewerb
    -1.83
    Bö
    -1.81
    ться
    -1.75
    POSITIVE LOGITS
    🧌
    2.88
    autogui
    2.38
    胧
    2.31
    
    2.30
    沅
    2.20
    独特的
    2.03
    volezza
    2.00
     afectadas
    1.99
     –
    1.94
    ή
    1.94
    Activations Density 0.005%

    No Known Activations