© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 4451
    Prev
    Next
    INDEX
    Explanations

    direitos e confiança

    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
    Use
    0.40
    Header
    0.39
    调
    0.39
    Điều
    0.39
    String
    0.38
    处理
    0.37
    Print
    0.37
    Nc
    0.36
    Dropdown
    0.36
    参数
    0.36
    POSITIVE LOGITS
     durante
    0.38
     E
    0.38
    0.37
     L
    0.37
     está
    0.36
     esté
    0.35
     unsustainable
    0.34
     Z
    0.34
     IEM
    0.34
     menor
    0.33
    Activations Density 0.179%

    No Known Activations