© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 166
    Prev
    Next
    INDEX
    Explanations

    Russian and German prefixes

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

    художественная литература, техника, наука

    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_53_width_65k_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
    𝗞
    0.54
    蟎
    0.54
     ಉತ್ಪನ್ನ
    0.53
    鋯
    0.53
     Elektrokhimiya
    0.52
    𝐬
    0.52
    鶚
    0.52
     SBOM
    0.51
     शुरुआ
    0.50
    ﺶ
    0.50
    POSITIVE LOGITS
    ↵
    0.54
    0.52
    on
    0.49
    it
    0.49
    &
    0.49
    and
    0.48
     ...
    0.48
     -
    0.48
    ene
    0.48
    p
    0.47
    Activations Density 0.028%

    No Known Activations