© 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. 36691
    Prev
    Next
    INDEX
    Explanations

    IMPORTANT DISCLAIMER

    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
     potom
    0.44
    صوص
    0.43
    ).*
    0.42
     később
    0.41
    િન
    0.40
    底部
    0.40
    =[
    0.39
     précédemment
    0.39
    䉼
    0.39
     চলবে
    0.38
    POSITIVE LOGITS
    вени
    0.42
    der
    0.39
    rif
    0.38
    Hers
    0.38
     похо
    0.37
    훤
    0.37
     годов
    0.37
    وتی
    0.37
    bble
    0.37
    кто
    0.36
    Activations Density 0.061%

    No Known Activations