© 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. 150024
    Prev
    Next
    INDEX
    Explanations

    comparison and relatedness

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

    resetting things with paperclip

    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
     opus
    0.49
    我会
    0.47
     imperatives
    0.46
    rige
    0.46
     filenames
    0.45
     будут
    0.45
    esque
    0.44
    욀
    0.44
     руководитель
    0.44
     subdir
    0.44
    POSITIVE LOGITS
    住所
    0.46
    annotation
    0.45
    ナ
    0.45
    visi
    0.43
     லட்சம்
    0.43
    ゔ
    0.43
     গোল
    0.42
     colon
    0.41
    ಲೆ
    0.41
     பெ
    0.41
    Activations Density 0.001%

    No Known Activations