© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 117453
    Prev
    Next
    INDEX
    Explanations

    designed to provide

    np_acts-logits-general · gemini-2.5-flash-lite

    associations of beauty and emotion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ෘ
    0.45
    ילו
    0.42
    ولا
    0.40
     kau
    0.40
    оло
    0.39
     Kau
    0.39
    ול
    0.38
     오히려
    0.38
    ول
    0.38
    䂧
    0.38
    POSITIVE LOGITS
    🎹
    0.47
    此同时
    0.46
     trùng
    0.45
    歌曲
    0.45
    ことを
    0.44
     песен
    0.44
    优先
    0.44
    保障
    0.43
     سننے
    0.43
     khán
    0.42
    Activations Density 0.002%

    No Known Activations