© 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. 49601
    Prev
    Next
    INDEX
    Explanations

    largest ice, precious cargo, typical poker

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

    specific phrases and keywords

    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
     Woodruff
    0.50
     Đức
    0.49
    anganese
    0.47
    ]=
    0.46
     विकिरण
    0.46
    CATEGORY
    0.46
     Cho
    0.45
     stockholders
    0.45
     Oo
    0.44
     ভ্যাক
    0.44
    POSITIVE LOGITS
     rejuven
    0.52
    لم
    0.50
    ná
    0.50
     remont
    0.49
     sá
    0.48
    ä
    0.46
     támogat
    0.46
    å
    0.46
    ：
    0.46
     verzi
    0.45
    Activations Density 0.000%

    No Known Activations