© 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. 33611
    Prev
    Next
    INDEX
    Explanations

    updates, accuracy, and fixing errors

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

    ensure data accuracy and updates

    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
    çı
    0.46
     tarde
    0.46
    晓
    0.45
    ļa
    0.43
    щи
    0.41
     sere
    0.41
     Backyard
    0.41
     Blooming
    0.41
     fără
    0.40
     khóa
    0.40
    POSITIVE LOGITS
    ተ
    0.45
     ক্রমাগত
    0.42
     ενη
    0.42
    update
    0.41
    得る
    0.41
     accuracy
    0.41
    uzu
    0.40
     update
    0.40
     અપ
    0.39
     अपडेट
    0.39
    Activations Density 0.002%

    No Known Activations