© 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. 70520
    Prev
    Next
    INDEX
    Explanations

    If you will not

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

    validation and status checking

    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
     швид
    0.52
    と一緒に
    0.50
    🌥
    0.50
    ו
    0.48
    🕌
    0.48
    这家
    0.47
    로우
    0.47
    这座
    0.47
    🏰
    0.47
     програ
    0.46
    POSITIVE LOGITS
     credentials
    0.54
     validity
    0.53
     credibility
    0.52
     paternity
    0.51
     mutable
    0.50
    ↵
    0.49
     legitimacy
    0.49
     mangle
    0.49
     separation
    0.48
     kür
    0.48
    Activations Density 0.001%

    No Known Activations