© 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. 32074
    Prev
    Next
    INDEX
    Explanations

    the earliest

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

    foreign words, scripts, and concepts

    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
    b
    0.58
    st
    0.58
     G
    0.58
    m
    0.56
    ta
    0.53
    me
    0.52
     B
    0.51
     Required
    0.49
     completed
    0.49
    der
    0.47
    POSITIVE LOGITS
     แน
    0.57
    ՜
    0.54
     olursa
    0.50
    ྷ
    0.50
    кансер
    0.49
     upheaval
    0.49
    罅
    0.48
    觧
    0.48
     желу
    0.48
    確率
    0.48
    Activations Density 0.000%

    No Known Activations