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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 2070
    Prev
    Next
    INDEX
    Explanations

    specific characters and other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     Utilisez
    0.51
     inmobili
    0.51
     അല്ലെങ്കിൽ
    0.50
     యొక్క
    0.47
     estadounidense
    0.45
     Использу
    0.45
     Информация
    0.45
    ߋ
    0.43
     proizvoda
    0.43
     표준
    0.43
    POSITIVE LOGITS
     troughs
    0.43
    simeq
    0.41
    gF
    0.41
     atrophy
    0.41
     overturn
    0.40
    WITT
    0.40
    itzt
    0.39
     со
    0.39
    ATIONAL
    0.39
     lambs
    0.39
    Activations Density 0.001%

    No Known Activations