© 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. 10951
    Prev
    Next
    INDEX
    Explanations

    lowest points and trends

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

    declining or slowing trends

    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
    ısı
    0.53
    饮食
    0.52
    协助
    0.50
    试
    0.50
    导入
    0.50
     安装
    0.48
    安装
    0.48
    运算
    0.48
     ısı
    0.48
     segítség
    0.48
    POSITIVE LOGITS
     peak
    0.54
    index
    0.52
    ピーク
    0.52
     decline
    0.51
     lows
    0.51
     declines
    0.51
    series
    0.48
    year
    0.48
    values
    0.48
     peaks
    0.48
    Activations Density 0.078%

    No Known Activations