© 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. 544
    Prev
    Next
    INDEX
    Explanations

    s followed by common words

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

    this is

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ла
    0.66
    ты
    0.66
    (
    0.62
    ти
    0.61
    ো
    0.58
     stockings
    0.54
    νει
    0.52
     sparsim
    0.52
     mishaps
    0.51
    ва
    0.50
    POSITIVE LOGITS
     is
    0.86
    d
    0.72
     was
    0.72
     de
    0.66
     an
    0.66
     que
    0.64
     à
    0.64
     are
    0.63
     ה
    0.62
    た
    0.61
    Activations Density 1.150%

    No Known Activations