© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5750
    Prev
    Next
    INDEX
    Explanations

    exploring themes of

    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_16k_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
    an
    0.81
    a
    0.70
    am
    0.63
    town
    0.62
    school
    0.62
    information
    0.62
    tur
    0.62
    to
    0.61
    l
    0.60
    p
    0.60
    POSITIVE LOGITS
     theme
    0.88
    Theme
    0.80
     Theme
    0.80
    Themes
    0.80
    主题
    0.79
     temática
    0.79
     themes
    0.77
     thème
    0.77
     tema
    0.76
     テーマ
    0.76
    Activations Density 0.088%

    No Known Activations