© 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. 27836
    Prev
    Next
    INDEX
    Explanations

    believe that

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

    non-english words

    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
    越
    0.43
    ym
    0.42
    ös
    0.41
    शत
    0.41
    やく
    0.41
    rels
    0.40
     meson
    0.39
    за
    0.39
    let
    0.39
    aneus
    0.38
    POSITIVE LOGITS
     eşit
    0.59
     ﺍﻟ
    0.57
     สิง
    0.54
     ﺍ
    0.53
     আগ্রহী
    0.50
     espect
    0.49
     habitudes
    0.49
     Ро
    0.49
     APPE
    0.49
     они
    0.48
    Activations Density 0.000%

    No Known Activations