© 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. 93626
    Prev
    Next
    INDEX
    Explanations

    fencing terms and maneuvers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     nuits
    -0.73
    ᠰ
    -0.73
    AFL
    -0.71
    Einsatz
    -0.69
     betul
    -0.68
     futbol
    -0.67
     Suomi
    -0.67
    蘋果
    -0.67
    𝒗
    -0.66
    azi
    -0.66
    POSITIVE LOGITS
     fencing
    2.00
     sword
    1.68
     Fencing
    1.50
     fence
    1.49
     fen
    1.40
     swords
    1.39
    🤺
    1.28
    sword
    1.24
     foil
    1.22
     fences
    1.21
    Activations Density 0.027%

    No Known Activations