© 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. 256866
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    IVIDUAL
    0.55
    женности
    0.49
    німа
    0.48
     Комп
    0.46
     कर्मचारी
    0.45
    鉋
    0.45
    ूज
    0.44
    管制
    0.44
     Фургал
    0.44
    ніза
    0.43
    POSITIVE LOGITS
     proofs
    0.48
     dependen
    0.48
    port
    0.47
     subcl
    0.47
     passionately
    0.46
    (
    0.46
    [
    0.45
     axis
    0.45
    bone
    0.45
     brooks
    0.45
    Activations Density 0.002%

    No Known Activations