© 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. 11752
    Prev
    Next
    INDEX
    Explanations

    describing events or conditions

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

    covers everything

    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
     käyttää
    0.55
     acqua
    0.45
     নিযুক্ত
    0.45
    確保
    0.45
    ジェル
    0.44
    ีย์
    0.44
    ৫
    0.44
     বজায়
    0.43
    हेही
    0.43
    鷸
    0.43
    POSITIVE LOGITS
    整个
    0.73
     the
    0.70
    整個
    0.66
    the
    0.63
     prostor
    0.62
     пространство
    0.61
     khắp
    0.61
     весь
    0.61
     streets
    0.59
     всю
    0.59
    Activations Density 0.086%

    No Known Activations