© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 16415
    Prev
    Next
    INDEX
    Explanations

    contrast and qualification

    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
    MessageNow
    0.58
    owości
    0.56
     కనిప
    0.52
    ጶ
    0.52
    Из
    0.52
     висо
    0.52
    ਤੀ
    0.52
    !">
    0.52
    🗨
    0.52
    𝘶
    0.51
    POSITIVE LOGITS
     but
    0.72
     only
    0.60
     and
    0.57
     have
    0.56
     complement
    0.54
     But
    0.52
     complementary
    0.52
     However
    0.50
     doesn
    0.50
     however
    0.50
    Activations Density 0.035%

    No Known Activations