© 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. 225742
    Prev
    Next
    INDEX
    Explanations

    contractual provisions and assistance

    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
    蒺
    0.60
     Epson
    0.56
     食器
    0.50
     输出
    0.49
     虽然
    0.49
     অষ্ট
    0.48
     vaikka
    0.48
     给
    0.47
     ampli
    0.46
     bagel
    0.46
    POSITIVE LOGITS
    é
    0.67
    mann
    0.60
    son
    0.53
    إ
    0.52
    í
    0.50
    ח
    0.49
    та
    0.48
     он
    0.48
    ain
    0.48
    im
    0.48
    Activations Density 0.000%

    No Known Activations