© 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. 114115
    Prev
    Next
    INDEX
    Explanations

    keep

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

    measuring amounts and concepts

    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
    S
    0.50
    9
    0.49
    3
    0.47
    G
    0.46
    desk
    0.46
    dialog
    0.45
    iak
    0.45
    6
    0.44
    5
    0.43
    Query
    0.43
    POSITIVE LOGITS
     établir
    0.58
     پیسې
    0.51
     celebrities
    0.50
     cuanto
    0.49
     antérieur
    0.48
     résultats
    0.48
    もっと
    0.48
    の新
    0.47
    .~\
    0.47
    ർ
    0.47
    Activations Density 0.001%

    No Known Activations