© 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. 203498
    Prev
    Next
    INDEX
    Explanations

    foreign or specific words

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

    not genuine direct

    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
    ﺶ
    0.45
    าก
    0.44
    νονται
    0.44
    ﻑ
    0.42
    raper
    0.41
    niu
    0.41
    ysl
    0.41
    preceq
    0.41
    ρα
    0.41
    susp
    0.41
    POSITIVE LOGITS
     új
    0.50
     відноси
    0.49
     aktual
    0.46
     Māori
    0.45
     ဗ
    0.44
     noncommutative
    0.44
     María
    0.43
     aromas
    0.43
     لڑکی
    0.42
     рассказа
    0.42
    Activations Density 0.000%

    No Known Activations