© 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. 80329
    Prev
    Next
    INDEX
    Explanations

    multi-lingual meaning apprehension

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

    enumerate parts or elements

    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
    H
    0.50
    welcome
    0.50
    PR
    0.48
     управління
    0.47
    R
    0.47
    GA
    0.46
    exam
    0.46
    ORA
    0.46
    G
    0.46
    whatever
    0.46
    POSITIVE LOGITS
     ඇති
    0.57
     perceive
    0.54
     perceives
    0.49
    પણ
    0.48
    تن
    0.47
     fosters
    0.47
    忉
    0.47
     conveys
    0.46
     grows
    0.46
     ي
    0.44
    Activations Density 0.000%

    No Known Activations