© 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. 108211
    Prev
    Next
    INDEX
    Explanations

    organizational details and customer information

    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
    -
    0.50
    an
    0.48
    ان
    0.46
     All
    0.45
    All
    0.44
    по
    0.44
    uns
    0.43
    t
    0.43
    5
    0.42
    I
    0.41
    POSITIVE LOGITS
     वैदिक
    0.50
    皚
    0.46
     पाठ्यक्रम
    0.46
     aprobación
    0.43
    RANGER
    0.42
     مصنوعی
    0.42
     micrófono
    0.42
     antifungal
    0.42
    KeyboardView
    0.42
     evolución
    0.41
    Activations Density 0.006%

    No Known Activations