© 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. 242320
    Prev
    Next
    INDEX
    Explanations

    plate, areas, measure, negative, white

    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
     けど
    0.45
    дом
    0.45
    dad
    0.44
    ACIÓN
    0.43
     確認
    0.43
    cw
    0.42
    規格
    0.42
    d
    0.42
     lactation
    0.41
    ců
    0.41
    POSITIVE LOGITS
    鹅
    0.47
     ilgili
    0.46
    Between
    0.45
     antara
    0.45
     dwóch
    0.45
    ⵥ
    0.45
    ättning
    0.44
    板块
    0.44
     aast
    0.44
     फ्रेंड्स
    0.44
    Activations Density 0.000%

    No Known Activations