© 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. 136253
    Prev
    Next
    INDEX
    Explanations

    book launch timetable

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

    never `*`

    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
    땔
    0.54
    ウス
    0.50
    ೇಕ
    0.49
    μάτων
    0.49
    碑
    0.49
    ાન
    0.49
    垢
    0.48
    としている
    0.48
    ﻟ
    0.47
    ตรี
    0.47
    POSITIVE LOGITS
    ela
    0.51
    aren
    0.49
    ung
    0.49
    ah
    0.48
    era
    0.48
    tey
    0.47
     AW
    0.47
    te
    0.47
    wam
    0.47
     Gee
    0.46
    Activations Density 0.000%

    No Known Activations