© 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. 60480
    Prev
    Next
    INDEX
    Explanations

    meuble tv pas cher

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

    Flip switch, hilly landscape

    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
     然后
    0.65
     معانا
    0.58
     يست
    0.57
     然後
    0.56
     现在
    0.54
     يصير
    0.53
     置
    0.52
     ហើយ
    0.52
     manglid
    0.52
     必要
    0.51
    POSITIVE LOGITS
    ા
    0.51
     ugg
    0.47
    plugin
    0.46
    guy
    0.44
    ୯
    0.43
    FRE
    0.43
    KILL
    0.43
    া
    0.41
    BLOG
    0.41
     oncologist
    0.41
    Activations Density 0.001%

    No Known Activations