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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15872
    Prev
    Next
    INDEX
    Explanations

    numbers or years

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

    bullet points

    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_16k_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
     તમારા
    0.53
    哫
    0.48
    醅
    0.47
    manın
    0.46
    鲔
    0.46
    企业的
    0.46
    囯
    0.46
    ეგის
    0.45
     თქვენ
    0.45
    阏
    0.45
    POSITIVE LOGITS
     d
    0.54
    0.53
    ↵↵
    0.53
     t
    0.53
     H
    0.53
     Y
    0.50
     R
    0.49
     G
    0.49
     and
    0.48
     g
    0.48
    Activations Density 0.010%

    No Known Activations