© 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. 86470
    Prev
    Next
    INDEX
    Explanations

    making time

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

    data type definitions

    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
    ၾ
    0.52
    Eye
    0.51
    Ev
    0.48
    Ey
    0.47
    Oral
    0.45
    璈
    0.45
    Overlay
    0.45
     eyeb
    0.44
     اکاؤنٹ
    0.44
    டுகள்
    0.44
    POSITIVE LOGITS
    تى
    0.49
    淢
    0.47
     Međutim
    0.46
    晝
    0.45
    وى
    0.44
     其中
    0.44
    nički
    0.44
     সংগ্রহের
    0.43
     ٣
    0.43
    مال
    0.43
    Activations Density 0.000%

    No Known Activations