© 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. 103872
    Prev
    Next
    INDEX
    Explanations

    SC requires

    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
    ي
    0.97
    ת
    0.90
    ز
    0.89
    ა
    0.87
    dır
    0.83
    ן
    0.82
     شما
    0.81
    ATE
    0.80
     pueden
    0.79
    n
    0.77
    POSITIVE LOGITS
     and
    0.78
    and
    0.76
    ంబేద్కర్
    0.71
    ographic
    0.70
    ೨
    0.68
     अभिनंदन
    0.65
     uncorrelated
    0.65
     ~\
    0.65
    ad
    0.64
    вши
    0.63
    Activations Density 0.002%

    No Known Activations