© 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. 179909
    Prev
    Next
    INDEX
    Explanations

    special offers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Lucille
    0.51
     Vue
    0.49
     Breathe
    0.47
     I
    0.47
     Wanda
    0.46
     Cherry
    0.46
     Urlaub
    0.45
     Apollo
    0.45
    惧
    0.45
    apur
    0.44
    POSITIVE LOGITS
    elem
    0.55
    siege
    0.53
    彌
    0.50
    christian
    0.50
    SEPARATOR
    0.49
    geojson
    0.48
    version
    0.48
    כות
    0.47
    κα
    0.47
    стран
    0.47
    Activations Density 0.001%

    No Known Activations