© 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. 4529
    Prev
    Next
    INDEX
    Explanations

    web addresses

    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
    t
    0.92
    on
    0.88
    as
    0.73
    an
    0.72
    ان
    0.71
    os
    0.70
    em
    0.68
    la
    0.66
    ى
    0.66
    es
    0.63
    POSITIVE LOGITS
    이스
    0.79
    ("|"+"
    0.75
     corrobor
    0.74
    "।
    0.71
     vivimos
    0.71
     ज़्यादा
    0.70
    ᄇ
    0.68
     defunct
    0.68
     свето
    0.68
    လမ်း
    0.67
    Activations Density 0.065%

    No Known Activations