© 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. 29705
    Prev
    Next
    INDEX
    Explanations

    lots of, japanese English

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

    describing body parts and development

    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
     ਨ
    0.56
     پ
    0.43
     impromptu
    0.41
     L
    0.41
    發現
    0.41
     セット
    0.41
     pierwsze
    0.41
    5
    0.41
    B
    0.40
     T
    0.40
    POSITIVE LOGITS
    我认为
    0.57
     বলেছে
    0.55
    has
    0.48
    认为
    0.47
    鲞
    0.46
    懑
    0.46
    建议
    0.46
    认为是
    0.46
    痱
    0.46
     বলেছেন
    0.46
    Activations Density 0.001%

    No Known Activations