© 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. 860
    Prev
    Next
    INDEX
    Explanations

    ad description

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     is
    1.14
     to
    0.82
     at
    0.76
     be
    0.71
    ায়
    0.65
     থেকে
    0.65
     of
    0.64
    是
    0.62
     a
    0.61
     on
    0.61
    POSITIVE LOGITS
    and
    0.70
    υ
    0.66
    us
    0.66
     propried
    0.65
    및
    0.63
    olded
    0.61
    ст
    0.59
    sofar
    0.59
    ம்
    0.59
    oltre
    0.57
    Activations Density 0.062%

    No Known Activations