© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 1832
    Prev
    Next
    INDEX
    Explanations

    trained or created by

    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_31_width_65k_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
    ूफ
    0.42
    อาจ
    0.38
    ത്തിലുള്ള
    0.37
     የመጀመሪያ
    0.35
    Rotatef
    0.35
     ensuring
    0.34
    U
    0.34
    柇
    0.34
    ական
    0.34
    Bou
    0.34
    POSITIVE LOGITS
    ت
    0.62
     by
    0.61
     in
    0.57
     from
    0.56
     recientemente
    0.55
    在了
    0.54
     with
    0.51
     przez
    0.51
    ed
    0.48
     بواسطة
    0.47
    Activations Density 0.290%

    No Known Activations