© 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. 48644
    Prev
    Next
    INDEX
    Explanations

    fighting, boxing, and battles

    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
    istiwa
    -0.88
     jogadores
    -0.86
     ministre
    -0.84
    superuser
    -0.84
    Incre
    -0.84
    Nguyễn
    -0.84
    campista
    -0.83
     phố
    -0.82
    🧽
    -0.81
     Послед
    -0.81
    POSITIVE LOGITS
    style
    0.90
    calculations
    0.84
    fname
    0.82
     calculations
    0.81
     predict
    0.80
    Hvem
    0.79
    chemistry
    0.77
     Calculations
    0.77
     style
    0.75
     insignificant
    0.75
    Activations Density 0.018%

    No Known Activations