Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 3031
    Prev
    Next
    INDEX
    Explanations

    numbers and commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    麝
    0.53
    टा
    0.49
     \(
    0.49
     witchcraft
    0.47
     함수의
    0.46
     Sph
    0.46
     
    0.46
     Seag
    0.46
     عبارت
    0.46
     അഭിപ്
    0.46
    POSITIVE LOGITS
    linkLabel
    0.57
    ppes
    0.56
    Ϊ
    0.56
    collections
    0.55
     पिस्टल
    0.55
    iegen
    0.54
    だった
    0.54
    私募基金管理人
    0.53
    ımız
    0.53
     الجميع
    0.53
    Activations Density 0.645%

    No Known Activations