© 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. 31909
    Prev
    Next
    INDEX
    Explanations

    ductwork

    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
    0.90
    ู
    0.83
    IN
    0.77
     coffee
    0.75
    ES
    0.72
    AR
    0.71
    ਰ
    0.69
    ט
    0.68
     asymmetric
    0.66
    ٹ
    0.66
    POSITIVE LOGITS
    bevel
    0.76
     начало
    0.68
     على
    0.68
    for
    0.67
    増や
    0.66
    _{
    0.66
    players
    0.65
    بخ
    0.64
     έχουν
    0.63
     ત્રણ
    0.63
    Activations Density 0.002%

    No Known Activations