© 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. 72687
    Prev
    Next
    INDEX
    Explanations

    marketing your services

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

    research and programming terms

    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
     hydrolyzed
    0.46
    ⵢ
    0.44
    栋
    0.43
    菄
    0.43
     cít
    0.42
    ഗോ
    0.42
    allowSlide
    0.42
     causada
    0.41
     najlepiej
    0.40
     বিদ্যমান
    0.40
    POSITIVE LOGITS
    _
    0.42
    XXXX
    0.41
    s
    0.41
     Broker
    0.39
     Chirop
    0.39
     BorderLayout
    0.38
     Rück
    0.38
    Broker
    0.38
    തോടെ
    0.38
     Students
    0.37
    Activations Density 0.000%

    No Known Activations