© 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. 145442
    Prev
    Next
    INDEX
    Explanations

    high density/activity

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

    technical classifications

    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
    то
    0.47
    エンジ
    0.46
    니까
    0.46
    鐙
    0.46
     WERE
    0.46
    ﻧ
    0.44
     탁
    0.44
     USS
    0.44
    อ
    0.43
    ضو
    0.42
    POSITIVE LOGITS
    óság
    0.53
    w
    0.52
    setUp
    0.50
     jelen
    0.48
    k
    0.48
    boards
    0.47
    kort
    0.47
     stellt
    0.46
     kez
    0.46
    ogt
    0.45
    Activations Density 0.001%

    No Known Activations