© 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. 152334
    Prev
    Next
    INDEX
    Explanations

    foreign language names and phrases

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

    if anything exists

    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
    ╾
    0.47
    กาย
    0.46
    )=
    0.45
    เส
    0.45
    มีการ
    0.43
    收入
    0.43
    aesthetic
    0.43
    ＝
    0.43
    उच्च
    0.43
    ถา
    0.43
    POSITIVE LOGITS
     Sht
    0.68
     Elles
    0.62
     Pierre
    0.57
     Ling
    0.55
     Dia
    0.55
     Zijn
    0.54
     Il
    0.54
     Dioc
    0.54
     Lah
    0.53
     Christians
    0.52
    Activations Density 0.000%

    No Known Activations