© 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. 29647
    Prev
    Next
    INDEX
    Explanations

    python code snippets

    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
     أس
    0.46
     प्राप्त
    0.44
    Sorter
    0.38
    种
    0.37
     أم
    0.37
     __________
    0.36
     عملی
    0.36
    Numerous
    0.36
     عملية
    0.35
     lên
    0.35
    POSITIVE LOGITS
     lava
    0.36
    𝒌
    0.36
     lied
    0.36
    […]
    0.35
     negat
    0.33
     fanno
    0.33
     Html
    0.33
    suptitle
    0.33
    лт
    0.32
    rootDir
    0.32
    Activations Density 0.009%

    No Known Activations