© 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. 107079
    Prev
    Next
    INDEX
    Explanations

    cooking surfaces

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

    crucial role in design

    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
     hogs
    0.44
     superl
    0.43
    l
    0.42
    asking
    0.41
    剰
    0.41
     acclimat
    0.40
    eas
    0.40
    eigen
    0.40
    ily
    0.39
     corridors
    0.39
    POSITIVE LOGITS
     关闭
    0.53
     打开
    0.51
     vudd
    0.50
     ແ
    0.49
     cuchar
    0.48
     contacto
    0.47
     获取
    0.47
     giác
    0.47
     informacion
    0.47
     cámaras
    0.46
    Activations Density 0.001%

    No Known Activations