© 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. 89522
    Prev
    Next
    INDEX
    Explanations

    Ministers, branding, communications, foreign

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

    Yes!

    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
    ร
    0.52
    м
    0.52
    க்தி
    0.50
    ем
    0.50
    Е
    0.48
     chiar
    0.47
    е
    0.46
    ম
    0.46
    ที่มี
    0.46
    г
    0.46
    POSITIVE LOGITS
     एजु
    0.48
     Ministers
    0.48
     Promotions
    0.47
     Communications
    0.46
     ちゃん
    0.46
     ministers
    0.45
     branding
    0.45
     Branding
    0.45
     pelanggan
    0.44
     व्या
    0.44
    Activations Density 0.000%

    No Known Activations