© 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. 144856
    Prev
    Next
    INDEX
    Explanations

    legal or technical clauses

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

    electrospinning

    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
    ഭ
    0.52
    ב
    0.51
    قر
    0.51
    し
    0.49
    Not
    0.48
    真的
    0.47
     erw
    0.47
    因为
    0.46
    قوم
    0.46
    Una
    0.46
    POSITIVE LOGITS
     Nantucket
    0.50
     Moul
    0.47
     минуты
    0.46
     captivity
    0.45
     esimerkiksi
    0.45
     გ
    0.44
    చ్చు
    0.44
    culoskeletal
    0.44
     وع
    0.43
     ഏക
    0.43
    Activations Density 0.000%

    No Known Activations