© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 122904
    Prev
    Next
    INDEX
    Explanations

    organelles and bacteria or separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ini
    0.50
     Books
    0.49
    /
    0.49
     Harvard
    0.48
    Books
    0.48
    Address
    0.47
     Address
    0.47
    will
    0.46
     Industry
    0.46
    |
    0.46
    POSITIVE LOGITS
     mutta
    0.63
     dentées
    0.57
     hivyo
    0.56
     conseguenza
    0.55
    rimos
    0.53
     کرو
    0.53
     მაგრამ
    0.52
     météor
    0.52
     somos
    0.51
    詁
    0.51
    Activations Density 0.002%

    No Known Activations