© 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. 34-GEMMASCOPE-RES-131K
    7. 48605
    Prev
    Next
    INDEX
    Explanations

    surf and surfing

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

    The neuron activates on occurrences of the substring “surf” (in any context or casing), i.e. it detects mentions of “surf,” “surfing,” “SurfWorks,” etc.

    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
    bilden
    -0.81
     której
    -0.81
    🅻
    -0.79
     takže
    -0.75
    を高
    -0.75
    annu
    -0.74
     remercie
    -0.73
    Carex
    -0.72
     APD
    -0.72
     wrestlers
    -0.71
    POSITIVE LOGITS
    🏄
    1.45
     surf
    1.30
    Sur
    1.14
     Surf
    1.14
    boards
    1.05
     Sur
    1.03
    Surf
    1.02
    side
    0.91
    surf
    0.91
    サー
    0.90
    Activations Density 0.011%

    No Known Activations