© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8365
    Prev
    Next
    INDEX
    Explanations

    list items and symbols

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

    etc., and so on

    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_40_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
    rophiles
    0.46
    Firstly
    0.46
    的第一
    0.45
     Firstly
    0.44
    ^{\#}\
    0.42
    First
    0.41
    neapolis
    0.38
     /**
    0.38
    issantes
    0.37
    Dougall
    0.37
    POSITIVE LOGITS
    *
    1.17
    *,
    0.63
    *}$
    0.62
    *',
    0.59
    *;
    0.53
    *",
    0.53
    *}\
    0.52
    <blockquote>
    0.49
    *_
    0.47
    *$
    0.47
    Activations Density 0.029%

    No Known Activations