© 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. 909
    Prev
    Next
    INDEX
    Explanations

    option 2

    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
    پ
    0.46
    الا
    0.46
     dots
    0.44
    0.44
    ро
    0.43
    SHO
    0.42
     документів
    0.40
    Cleared
    0.39
    Data
    0.39
     outliers
    0.39
    POSITIVE LOGITS
    neſs
    0.53
    urney
    0.52
     redução
    0.49
    anç
    0.49
    Ս
    0.49
     தங்க
    0.48
     vár
    0.47
    IFORN
    0.47
    ۪
    0.46
     посвящён
    0.46
    Activations Density 0.109%

    No Known Activations