© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 48427
    Prev
    Next
    INDEX
    Explanations

    out with, out in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    媺
    0.47
    不去
    0.45
    蜘蛛
    0.44
     kiz
    0.43
    璎
    0.43
    茷
    0.42
    旂
    0.42
     കർ
    0.41
    剡
    0.41
     роки
    0.41
    POSITIVE LOGITS
    RE
    0.58
     Origins
    0.52
     Great
    0.52
     Trans
    0.51
    ικ
    0.51
    ﺭ
    0.49
    rs
    0.49
     интересно
    0.49
     GREAT
    0.48
     Old
    0.48
    Activations Density 0.000%

    No Known Activations