© 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. 13636
    Prev
    Next
    INDEX
    Explanations

    numerical ranges and percentages

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

    numbers, ratings, lists

    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
    一天
    0.42
    _
    0.38
    1
    0.38
    な
    0.38
     छह
    0.37
     overtake
    0.37
     ca
    0.36
    分
    0.36
    約
    0.36
    time
    0.35
    POSITIVE LOGITS
    ముల
    0.46
    وشی
    0.43
     马
    0.41
     ሰው
    0.40
     为了
    0.40
     İz
    0.39
     والم
    0.39
     phù
    0.39
     ตุ
    0.39
     مناسب
    0.38
    Activations Density 0.022%

    No Known Activations