© 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. 11134
    Prev
    Next
    INDEX
    Explanations

    many or largest

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

    explaining history or context

    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
    r
    0.54
    ành
    0.53
    y
    0.48
    à
    0.47
    ığında
    0.47
     hurried
    0.47
    õi
    0.46
     मानी
    0.45
     Thur
    0.45
    ronom
    0.44
    POSITIVE LOGITS
    さまざまな
    0.49
    ミュージック
    0.46
    숑
    0.46
    人事
    0.44
    たくさんの
    0.44
    クリニック
    0.43
     Japon
    0.43
    مص
    0.43
     przej
    0.43
    ジェット
    0.42
    Activations Density 0.000%

    No Known Activations