© 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. 218113
    Prev
    Next
    INDEX
    Explanations

    run it, teach you, review the

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

    seasons and cycles

    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
     kilometres
    0.44
     bleak
    0.44
     CHAS
    0.43
     pollut
    0.43
     ugljik
    0.42
     inwards
    0.42
     homotopy
    0.42
    ㎞
    0.42
    ResBuffer
    0.41
     incertid
    0.41
    POSITIVE LOGITS
    3
    0.53
    。
    0.49
    8
    0.46
    5
    0.45
    uu
    0.45
    6
    0.45
    7
    0.44
    兼用
    0.44
     trois
    0.44
    だけど
    0.43
    Activations Density 0.001%

    No Known Activations