© 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. 186652
    Prev
    Next
    INDEX
    Explanations

    names with Jr

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

    classic movies

    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
     그대로
    0.58
    ixel
    0.47
    佅
    0.46
    anding
    0.44
     indemn
    0.43
     thi
    0.43
    렛
    0.43
    iquant
    0.43
    ückt
    0.43
     येऊ
    0.43
    POSITIVE LOGITS
    Gonzalez
    0.54
    ْت
    0.47
    A
    0.47
    Marin
    0.46
    Mead
    0.46
    Memor
    0.46
    Hoff
    0.45
    H
    0.45
    ウ
    0.45
     показывает
    0.45
    Activations Density 0.001%

    No Known Activations