© 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. 64039
    Prev
    Next
    INDEX
    Explanations

    generally preferred

    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
     are
    0.65
     vielen
    0.64
     a
    0.61
     Often
    0.60
     ofte
    0.59
     be
    0.57
     often
    0.56
    ↵↵
    0.55
     Mohamed
    0.55
    s
    0.54
    POSITIVE LOGITS
    xcol
    0.63
     ಸುಮ
    0.61
    қта
    0.60
    ورہ
    0.58
    cPix
    0.58
     থাকিলে
    0.58
    ור
    0.57
    ರ
    0.57
    кте
    0.56
    ᱖
    0.55
    Activations Density 0.081%

    No Known Activations