© 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. 89857
    Prev
    Next
    INDEX
    Explanations

    dance floor lyrics

    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
    DIE
    0.51
     constraining
    0.49
    针对
    0.49
    多个
    0.47
    ında
    0.44
     ሥ
    0.44
    你想
    0.44
    约束
    0.44
    鬼
    0.44
     reconstructions
    0.43
    POSITIVE LOGITS
     Existem
    0.48
    ')){
    0.46
    mostly
    0.46
     Gaulle
    0.46
     Kumb
    0.46
     Clearance
    0.45
     PBS
    0.45
     FOB
    0.45
     Este
    0.45
     LEON
    0.45
    Activations Density 0.002%

    No Known Activations