© 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. 40950
    Prev
    Next
    INDEX
    Explanations

    bunk beds, bantu education, hanker

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

    links within parentheses

    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
    re
    0.76
    น
    0.72
    K
    0.66
    m
    0.64
    th
    0.64
    ن
    0.63
    li
    0.61
    V
    0.60
    to
    0.58
    acks
    0.58
    POSITIVE LOGITS
    다는
    0.63
     cheg
    0.60
     riten
    0.60
    다면
    0.57
    >
    0.57
    ৫
    0.57
    つの
    0.56
     koleg
    0.56
    тного
    0.55
    けた
    0.55
    Activations Density 0.407%

    No Known Activations