© 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-262K
    7. 38867
    Prev
    Next
    INDEX
    Explanations

    LLM models compatible

    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_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
     главным
    0.45
    package
    0.45
    ésie
    0.44
    ándole
    0.44
     하고
    0.44
    ліся
    0.43
     أكتوبر
    0.43
    🧾
    0.43
    loose
    0.43
    ledo
    0.42
    POSITIVE LOGITS
     PA
    0.48
    h
    0.48
    l
    0.46
     commutes
    0.45
     steroids
    0.44
     vermel
    0.44
     Derived
    0.43
     derives
    0.41
     prolifer
    0.41
     ops
    0.41
    Activations Density 0.000%

    No Known Activations