© 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. 49478
    Prev
    Next
    INDEX
    Explanations

    carridescalesroundsfact

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

    units of measure and related 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
    Перед
    0.57
    Setelah
    0.53
    Yeni
    0.53
    تال
    0.52
    İ
    0.51
    Př
    0.50
    અ
    0.50
    Sebelum
    0.50
    ر
    0.50
    වර
    0.49
    POSITIVE LOGITS
     yea
    0.50
     посе
    0.50
    ietic
    0.48
    h
    0.47
    ности
    0.45
    ppe
    0.45
    legraph
    0.45
     послу
    0.45
     тех
    0.44
    cings
    0.44
    Activations Density 0.000%

    No Known Activations