© 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. 103522
    Prev
    Next
    INDEX
    Explanations

    Pursuing

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

    rug colors, deviation from mean

    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
    b
    0.57
    o
    0.54
    a
    0.54
    ad
    0.53
    Internet
    0.51
    bord
    0.51
    lu
    0.48
    gul
    0.47
    dur
    0.46
    mis
    0.45
    POSITIVE LOGITS
    ྥ
    0.52
    チック
    0.50
    蓍
    0.50
    BlockUsed
    0.49
    ︽
    0.49
    傕
    0.48
    燹
    0.47
     hysterical
    0.46
    ᑖ
    0.46
    欷
    0.46
    Activations Density 0.001%

    No Known Activations