© 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. 156712
    Prev
    Next
    INDEX
    Explanations

    child/children contexts

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

    legal, ethical, technical reasoning

    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
    replic
    0.46
    남
    0.46
     fährt
    0.44
    ολ
    0.44
    ब
    0.44
    第三
    0.43
    ehl
    0.43
    έ
    0.43
    ted
    0.42
    第二
    0.42
    POSITIVE LOGITS
    ्रेंस
    0.47
     প্রস্ত
    0.46
     虽然
    0.45
     exorbit
    0.44
     wishlist
    0.44
     soften
    0.44
    ENSITY
    0.42
    orado
    0.41
     Etsy
    0.41
     இதுபோன்ற
    0.41
    Activations Density 0.001%

    No Known Activations