© 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. 218129
    Prev
    Next
    INDEX
    Explanations

    teaching, virtue, Ltd, Proust

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

    seeking meaning and solutions

    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
     Loose
    0.46
    AID
    0.45
     warahmatullahi
    0.45
     کە
    0.45
     irregularity
    0.42
     Wight
    0.42
     stycznia
    0.41
    ﹗
    0.40
    际
    0.40
     pitch
    0.39
    POSITIVE LOGITS
    cij
    0.63
    solver
    0.53
    auen
    0.53
     financieras
    0.50
    ueger
    0.50
     cheveux
    0.49
    franz
    0.49
    encrypted
    0.49
    uws
    0.49
     neun
    0.49
    Activations Density 0.000%

    No Known Activations