© 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. 180562
    Prev
    Next
    INDEX
    Explanations

    different compounds or factors

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

    colorful picture/drawing

    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
    ā
    0.57
    í
    0.55
    anggap
    0.52
    ów
    0.48
    i
    0.47
    ene
    0.47
    jen
    0.47
    unas
    0.46
    ām
    0.46
    ė
    0.46
    POSITIVE LOGITS
     symplect
    0.50
     море
    0.48
     hydrothermal
    0.48
     terroir
    0.47
     ocean
    0.47
     labyr
    0.46
    潛
    0.46
     psychos
    0.46
     symbolize
    0.45
    辭
    0.45
    Activations Density 0.000%

    No Known Activations