© 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. 28649
    Prev
    Next
    INDEX
    Explanations

    separate sides

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

    angled slightly

    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
    那我們
    0.46
    Ｇ
    0.45
    थाम
    0.43
    吶
    0.43
    錆
    0.42
    ﾛ
    0.42
    呐
    0.41
     принято
    0.41
    mittance
    0.40
    ﾏ
    0.40
    POSITIVE LOGITS
     übrigens
    0.54
     separate
    0.52
     ayrıca
    0.49
     Separate
    0.46
     separately
    0.45
     veden
    0.45
     separ
    0.44
     separable
    0.43
     unconnected
    0.43
    separate
    0.42
    Activations Density 0.000%

    No Known Activations