© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 687
    Prev
    Next
    INDEX
    Explanations

    motorcycle brands and models

    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
    κρα
    -0.77
     Chassis
    -0.74
    ttet
    -0.72
     surgir
    -0.72
     ORIG
    -0.72
     racing
    -0.72
     Tuesdays
    -0.71
     Jurassic
    -0.71
     Kole
    -0.70
    ambién
    -0.70
    POSITIVE LOGITS
     GL
    0.90
     Glenn
    0.85
     Shadow
    0.81
    ność
    0.79
     Kud
    0.79
    Glenn
    0.75
     GW
    0.74
     Saber
    0.72
    Shadow
    0.71
     Bergman
    0.71
    Activations Density 0.007%

    No Known Activations