© 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. 132025
    Prev
    Next
    INDEX
    Explanations

    instead of

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

    proactive reputation management

    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
     penetrates
    0.46
    agues
    0.44
     quickly
    0.42
     SUPPLEMENT
    0.42
     denotes
    0.42
    빌
    0.42
     Century
    0.41
     OW
    0.39
     glorious
    0.39
    ewise
    0.39
    POSITIVE LOGITS
    Фор
    0.52
     profe
    0.51
     appli
    0.51
    Ǻ
    0.51
     oración
    0.50
     Фор
    0.49
    евна
    0.49
     standart
    0.49
    褙
    0.49
     Dragonfly
    0.48
    Activations Density 0.000%

    No Known Activations