© 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. 43326
    Prev
    Next
    INDEX
    Explanations

    character development

    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
    ש
    0.50
     juegan
    0.46
     campos
    0.45
    पि
    0.45
    ق
    0.45
    in
    0.44
    ADESH
    0.44
    Excluded
    0.44
     instalar
    0.44
    h
    0.44
    POSITIVE LOGITS
     一
    0.52
     来
    0.52
     weld
    0.50
     vaporization
    0.49
     ଦ
    0.47
     بیش
    0.46
     एंटी
    0.46
     來
    0.45
     لے
    0.45
     ل
    0.45
    Activations Density 0.001%

    No Known Activations