© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 163645
    Prev
    Next
    INDEX
    Explanations

    motorcycle, bike, moto

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

    transaction validators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gesamt
    0.60
    த்தன
    0.54
    ቹን
    0.50
    intaan
    0.48
     前回
    0.46
    itements
    0.46
    UserProg
    0.45
    总
    0.44
     بتوان
    0.43
    akukannya
    0.43
    POSITIVE LOGITS
     teorie
    0.50
     species
    0.50
     motorcycle
    0.49
    bike
    0.45
     teorema
    0.45
     biofuels
    0.45
     Bike
    0.44
     moto
    0.44
     theorists
    0.43
     biofuel
    0.43
    Activations Density 0.000%

    No Known Activations