© 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. 208892
    Prev
    Next
    INDEX
    Explanations

    book covers, dishwasher pods, Queen Anne

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

    structured lists

    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
    nilai
    0.49
    Fle
    0.47
     human
    0.46
     apparaissent
    0.44
    უნქ
    0.44
    梅里
    0.43
     sparing
    0.42
    м
    0.42
    aspis
    0.42
    稍
    0.42
    POSITIVE LOGITS
     సర
    0.50
     সমর
    0.49
     BasicContainer
    0.48
     जर्नल
    0.46
     ట్ర
    0.46
    <unused38>
    0.45
     бк
    0.45
     忄
    0.45
     सेमेस्टर
    0.43
     మ‌
    0.43
    Activations Density 0.000%

    No Known Activations