© 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. 881
    Prev
    Next
    INDEX
    Explanations

    a followed by descriptive noun/adjective

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

    identifying descriptive adjectives

    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
    (
    0.55
     wings
    0.49
     software
    0.48
     syllables
    0.47
    {//
    0.45
     watt
    0.44
     genes
    0.44
     gears
    0.43
     urine
    0.43
     woodlands
    0.43
    POSITIVE LOGITS
    in
    0.70
    i
    0.61
    big
    0.53
    rod
    0.53
    deserialize
    0.53
    itation
    0.52
    ut
    0.52
     Warsz
    0.52
    of
    0.52
    it
    0.51
    Activations Density 0.242%

    No Known Activations