© 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. 31-GEMMASCOPE-2-RES-262K
    7. 193061
    Prev
    Next
    INDEX
    Explanations

    app, mounted, gift, once, little

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

    time browsing

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ‹
    0.62
     isotonic
    0.60
    ότερα
    0.55
     sulphate
    0.54
     bicarbonate
    0.54
     oxyd
    0.53
     anticoagulant
    0.53
     evanescent
    0.53
     admir
    0.52
     resuspended
    0.52
    POSITIVE LOGITS
    n
    0.58
    name
    0.54
    I
    0.50
    he
    0.48
    am
    0.48
    aj
    0.46
    ks
    0.46
    require
    0.46
    mts
    0.46
     do
    0.46
    Activations Density 0.001%

    No Known Activations