© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 239987
    Prev
    Next
    INDEX
    Explanations

    categories of products

    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
    Not in Any Lists

    No Comments

    Negative Logits
     aliphatic
    0.49
    akoti
    0.47
    পতি
    0.46
    جاتا
    0.46
     tendrás
    0.45
     ℝ
    0.43
    getSaveLocation
    0.43
    ppins
    0.41
    deer
    0.41
     rém
    0.41
    POSITIVE LOGITS
    この
    0.55
    こな
    0.52
    いろんな
    0.52
    Waiting
    0.51
    ページ
    0.48
    ปัจจุบัน
    0.48
    m
    0.48
    Iy
    0.47
    る
    0.47
    イメージ
    0.47
    Activations Density 0.000%

    No Known Activations