© 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. 40-GEMMASCOPE-2-RES-262K
    7. 111484
    Prev
    Next
    INDEX
    Explanations

    high score focus

    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_40_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
     bài
    0.39
    ताना
    0.38
     tamp
    0.38
    倏
    0.37
    ть
    0.37
     Back
    0.37
     contamin
    0.37
     yol
    0.36
    机械
    0.36
     tillbaka
    0.36
    POSITIVE LOGITS
    ლებელია
    0.50
    ⓞ
    0.40
     educators
    0.40
    臤
    0.40
     Gales
    0.39
    iga
    0.39
    ্যাম
    0.39
     ಇದರ
    0.39
     युवाओ
    0.39
    悹
    0.39
    Activations Density 0.000%

    No Known Activations