© 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. 157295
    Prev
    Next
    INDEX
    Explanations

    core, both, aggravation, try, asked, TDS, tee

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

    highlights severity

    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
    cies
    0.46
     않은
    0.46
    の新
    0.44
     appe
    0.43
     위
    0.43
     신
    0.43
    мента
    0.41
     않
    0.41
    している
    0.41
    않
    0.41
    POSITIVE LOGITS
     đủ
    0.48
    足够
    0.45
    تباينه
    0.43
     poderão
    0.43
     modos
    0.43
    足够的
    0.43
     môžu
    0.42
     могат
    0.41
    ostí
    0.41
    :_
    0.41
    Activations Density 0.001%

    No Known Activations