© 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. 249925
    Prev
    Next
    INDEX
    Explanations

    information about you

    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
    ティ
    0.54
    agian
    0.51
    গ
    0.49
    কৃ
    0.48
    6
    0.48
    ung
    0.48
    িজ
    0.47
     Brits
    0.47
    ๘
    0.46
     Explained
    0.46
    POSITIVE LOGITS
    尽快
    0.46
     obey
    0.46
    чної
    0.44
    谆
    0.43
    豪华
    0.42
    救援
    0.42
    괘
    0.42
    érons
    0.41
     abide
    0.41
    撇
    0.41
    Activations Density 0.000%

    No Known Activations