© 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. 41-GEMMASCOPE-2-RES-262K
    7. 219
    Prev
    Next
    INDEX
    Explanations

    designed for

    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_all/layer_41_width_262k_l0_big
    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
    ើន
    0.54
    OURCES
    0.54
    ンス
    0.52
     quelquefois
    0.50
    និច
    0.50
    IENCE
    0.49
     sobald
    0.48
    េ
    0.47
    ណ៌
    0.47
     stále
    0.47
    POSITIVE LOGITS
     Designed
    0.67
     designed
    0.64
     Specifically
    0.64
     specifically
    0.62
     להיות
    0.58
    to
    0.58
    in
    0.57
     deliberately
    0.57
     to
    0.56
    Designed
    0.55
    Activations Density 0.003%

    No Known Activations