© 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. 235506
    Prev
    Next
    INDEX
    Explanations

    customer support

    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
    狀態
    0.50
     остальные
    0.47
     cend
    0.45
     tấm
    0.44
     MAST
    0.44
     क्रमांका
    0.44
     сделали
    0.43
    暝
    0.43
     ›
    0.42
    旯
    0.42
    POSITIVE LOGITS
    UN
    0.53
    idy
    0.52
    ons
    0.50
    IN
    0.50
    EM
    0.49
    ree
    0.48
    ge
    0.46
    Y
    0.46
    te
    0.46
    riends
    0.46
    Activations Density 0.000%

    No Known Activations