© 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. 94923
    Prev
    Next
    INDEX
    Explanations

    loss, plan, wins

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

    after studies

    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
     zoomed
    0.46
     स्तन
    0.45
    とっても
    0.45
    音
    0.45
    ϱ
    0.45
    ピアノ
    0.45
     ভরে
    0.45
    妇
    0.45
    なんで
    0.44
    梱包
    0.44
    POSITIVE LOGITS
    uck
    0.46
    ist
    0.45
    UBE
    0.44
     Side
    0.44
     arm
    0.43
     Selección
    0.43
    erez
    0.43
     tar
    0.43
     Ste
    0.42
     feder
    0.42
    Activations Density 0.000%

    No Known Activations