© 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. 58121
    Prev
    Next
    INDEX
    Explanations

    turn or transfer

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

    The neuron strongly activates on words (and sub‐word pieces) that denote the concept of “turn” or “rotate” (e.g. turn, turns, turning, giro, rodar, etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    sandalia
    -2.20
    鴬
    -2.06
    0
    -1.99
     erstes
    -1.98
     aqueles
    -1.93
    ഀ
    -1.91
    
    -1.80
    荷物
    -1.75
    人には
    -1.74
     alimentazione
    -1.74
    POSITIVE LOGITS
      
    2.44
    </strong>
    2.23
    rightarrow
    2.08
    The
    1.99
    ของ
    1.93
    匝
    1.90
    <strong>
    1.89
     nią
    1.86
    setcounter
    1.80
    räge
    1.79
    Activations Density 0.016%

    No Known Activations