© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10813
    Prev
    Next
    INDEX
    Explanations

    Russian scientific and technical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lihtsalt
    0.51
     bardzo
    0.46
     chodzi
    0.46
     :+:
    0.45
     ł
    0.45
    古い
    0.45
     Preto
    0.44
     Liao
    0.43
     enthous
    0.43
    ži
    0.42
    POSITIVE LOGITS
     функциони
    0.51
     иннова
    0.51
     научно
    0.50
     перспек
    0.50
     ইউজ
    0.47
     Национа
    0.47
     техно
    0.46
     Г
    0.46
     комплекс
    0.46
     СП
    0.46
    Activations Density 0.056%

    No Known Activations