© 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. 1761
    Prev
    Next
    INDEX
    Explanations

    Serve any

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

    help me

    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
     premiums
    0.42
    優秀
    0.40
     인터넷
    0.40
    📱
    0.39
     peti
    0.38
     tsunami
    0.38
    著名的
    0.38
    장의
    0.37
    큽
    0.37
     페
    0.37
    POSITIVE LOGITS
    arranty
    0.49
    implicitly
    0.39
     could
    0.38
     ग्लूको
    0.38
     przykład
    0.37
    ंध्र
    0.37
     کوډ
    0.37
    ystycz
    0.36
     क्रोध
    0.36
     rattled
    0.36
    Activations Density 0.000%

    No Known Activations