© 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. 10516
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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
    корд
    0.72
    ಕಾರಿ
    0.66
     विकार
    0.66
    イス
    0.63
    гистра
    0.63
     prefque
    0.63
    પ
    0.62
    лять
    0.62
    роки
    0.62
     acides
    0.62
    POSITIVE LOGITS
     of
    0.93
    0
    0.81
    :
    0.78
    ing
    0.75
    us
    0.72
    %
    0.72
     that
    0.71
    ate
    0.68
    eli
    0.66
    ation
    0.65
    Activations Density 0.089%

    No Known Activations