© 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. 50110
    Prev
    Next
    INDEX
    Explanations

    reducing. largely. jackpot. ducted. made

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

    communication, songs, ideas, cop

    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
     kemungkinan
    0.48
     sociale
    0.46
     toucher
    0.46
     größ
    0.46
     û
    0.46
     menger
    0.45
     yalnız
    0.44
     filede
    0.44
     checkered
    0.42
     déchir
    0.42
    POSITIVE LOGITS
    雰
    0.48
    １
    0.47
     професси
    0.47
    の商品は
    0.46
    dust
    0.44
    眹
    0.44
     Amat
    0.43
     தாம்
    0.43
    旦
    0.43
    ١
    0.43
    Activations Density 0.000%

    No Known Activations