© 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. 220609
    Prev
    Next
    INDEX
    Explanations

    buyer-managers and suppliers

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

    GCP, corona, jeans

    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
    收
    0.52
    ۲
    0.51
    ود
    0.50
    幫
    0.50
     خرج
    0.49
    發
    0.48
    供
    0.47
    ила
    0.46
    莧
    0.46
    خلص
    0.46
    POSITIVE LOGITS
    icolored
    0.52
     neutrons
    0.51
    ş
    0.49
    neapolis
    0.49
     inasmuch
    0.48
    asible
    0.48
     ?.
    0.48
    iin
    0.48
    anse
    0.47
     tuf
    0.47
    Activations Density 0.000%

    No Known Activations