© 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. 30909
    Prev
    Next
    INDEX
    Explanations

    TV Guide

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

    say something

    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
     mani
    0.44
     Chanc
    0.44
     Prince
    0.43
     socios
    0.43
    intos
    0.43
    sina
    0.43
    蒟
    0.43
     hice
    0.41
     fur
    0.41
     revolutions
    0.41
    POSITIVE LOGITS
     かわいい
    0.55
    RANGER
    0.53
     เนื่องจาก
    0.53
     నే
    0.49
     صدای
    0.48
    目录
    0.46
     可愛い
    0.46
     ഉ
    0.46
    は
    0.46
    員
    0.46
    Activations Density 0.000%

    No Known Activations