© 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. 575
    Prev
    Next
    INDEX
    Explanations

    colours and tones

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

    color and shades

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

    colour

    np_max-act-logits · claude-4-5-sonnetTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     or
    0.51
     masyarakat
    0.51
    ی
    0.50
     metabolism
    0.48
     tekanan
    0.47
     downsizing
    0.47
    ::
    0.46
     in
    0.45
    *.
    0.45
     $
    0.45
    POSITIVE LOGITS
     couleurs
    0.81
     colores
    0.62
    em
    0.61
    colours
    0.59
    و
    0.58
     colours
    0.57
    色的
    0.57
     Farbe
    0.56
     Sólo
    0.55
     Farb
    0.55
    Activations Density 2.918%

    No Known Activations