© 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. 16-GEMMASCOPE-2-RES-262K
    7. 31399
    Prev
    Next
    INDEX
    Explanations

    atom's properties and function

    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_16_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
    as
    0.77
    ou
    0.70
    the
    0.68
    os
    0.67
    ia
    0.67
    အ
    0.67
     dioxygen
    0.66
    it
    0.66
    un
    0.62
    time
    0.62
    POSITIVE LOGITS
    '
    0.73
    )
    0.61
    ↵
    0.61
     certificado
    0.60
    hock
    0.60
    اه
    0.59
     minimale
    0.59
    рт
    0.59
    кай
    0.59
     pH
    0.58
    Activations Density 0.007%

    No Known Activations