© 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. 104588
    Prev
    Next
    INDEX
    Explanations

    factors, linking, win

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

    expanding theirmust behuge bitesmistake

    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
    對方
    0.54
    かの
    0.52
    ل
    0.51
    鎳
    0.50
    कौन
    0.49
    鎵
    0.49
    鉅
    0.48
    र्ग
    0.48
    ピック
    0.48
    給
    0.47
    POSITIVE LOGITS
     connexes
    0.44
    Hints
    0.43
     glossary
    0.42
     ascii
    0.42
     be
    0.40
    dire
    0.39
     ইউ
    0.39
    0
    0.38
    Insets
    0.38
    demos
    0.38
    Activations Density 0.000%

    No Known Activations