© 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. 67687
    Prev
    Next
    INDEX
    Explanations

    using or style

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

    using or choice of options

    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
    ೫
    0.49
     equities
    0.48
     შეიძლება
    0.48
     عالمی
    0.47
     inequities
    0.46
     festgestellt
    0.46
     mengangkat
    0.45
    銛
    0.45
    सूचित
    0.44
     renversement
    0.44
    POSITIVE LOGITS
    或
    0.60
    或是
    0.54
     or
    0.54
     using
    0.52
    Style
    0.52
     USING
    0.49
     বা
    0.48
     أو
    0.48
    Mode
    0.48
    Use
    0.48
    Activations Density 0.000%

    No Known Activations