© 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. 137957
    Prev
    Next
    INDEX
    Explanations

    markdown headings and structure

    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
    ۰۰
    0.67
    ০০
    0.61
    ᙱ
    0.55
     bilinear
    0.55
     lỗ
    0.54
     semidefinite
    0.54
     जर
    0.53
     permittivity
    0.53
     dilation
    0.52
    ००
    0.52
    POSITIVE LOGITS
    es
    0.83
    ס
    0.79
    ي
    0.74
    ย
    0.74
    al
    0.70
     it
    0.68
    ma
    0.68
    assets
    0.66
    to
    0.65
    也
    0.65
    Activations Density 0.000%

    No Known Activations