© 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. 126431
    Prev
    Next
    INDEX
    Explanations

    monthly topical offers

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

    parents, relationships, cause

    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
     in
    0.52
     interdiscipl
    0.48
     Xcode
    0.47
     o
    0.46
     understatement
    0.46
     сучас
    0.46
    ジュ
    0.46
     ri
    0.45
     r
    0.45
     XIII
    0.45
    POSITIVE LOGITS
     largura
    0.45
    pitch
    0.43
    ಗಳಿವೆ
    0.42
    carriers
    0.41
    ادرات
    0.41
    পথ
    0.41
    weil
    0.40
    нений
    0.40
    করিতে
    0.40
    weile
    0.39
    Activations Density 0.000%

    No Known Activations