© 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. 59767
    Prev
    Next
    INDEX
    Explanations

    training, want, idea

    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
     ಪ್ರದೇಶ
    0.63
     দেখিয়া
    0.52
    ştur
    0.50
    两侧
    0.50
    醝
    0.50
     двох
    0.49
     анд
    0.49
    fdPar
    0.49
    schw
    0.48
     фактор
    0.48
    POSITIVE LOGITS
    le
    0.47
    l
    0.46
     playback
    0.46
    te
    0.45
    ង្វ
    0.45
     would
    0.44
    h
    0.43
     dapat
    0.43
     hev
    0.43
    hops
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.