© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 723
    Prev
    Next
    INDEX
    Explanations

    ardle

    np_acts-logits-general · gemini-2.5-flash-lite

    HTML title content

    np_acts-logits-general · gemini-2.5-flash-lite

    technical specifications

    np_max-act-logits · claude-4-5-sonnet
    Triggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     to
    0.72
     on
    0.67
     barista
    0.59
    을
    0.59
    ות
    0.57
     of
    0.57
     עם
    0.57
    ెస్
    0.57
     중에
    0.57
     antioxidant
    0.56
    POSITIVE LOGITS
    that
    0.77
    for
    0.77
    us
    0.74
    and
    0.71
    ou
    0.70
    om
    0.70
    و
    0.70
    ib
    0.66
    ku
    0.64
    ig
    0.64
    Activations Density 5.220%

    No Known Activations