© 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. 37316
    Prev
    Next
    INDEX
    Explanations

    just or free

    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
    ieben
    0.44
    夢
    0.44
     للا
    0.43
    این
    0.41
    नु
    0.41
    ≖
    0.41
    ᓱ
    0.40
    could
    0.40
    法
    0.39
    суа
    0.39
    POSITIVE LOGITS
     систему
    0.45
     kilometers
    0.44
     değişiklik
    0.42
    পাড়া
    0.40
     Specialties
    0.40
     horsepower
    0.39
     पकड़
    0.39
     borg
    0.39
     topography
    0.39
     sizlere
    0.39
    Activations Density 0.003%

    No Known Activations