© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 35788
    Prev
    Next
    INDEX
    Explanations

    dividing into groups

    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_40_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
     هڪ
    0.47
     βρίσκεται
    0.44
     находится
    0.44
     له‌
    0.41
     பயணி
    0.41
     تون
    0.41
    जल
    0.40
    ჷ
    0.40
    เจอ
    0.40
    ኬ
    0.39
    POSITIVE LOGITS
     groups
    0.70
     Groups
    0.67
    Groups
    0.62
     groupes
    0.61
     grouping
    0.61
     completely
    0.61
     grouped
    0.60
     groupings
    0.59
     grupos
    0.59
     групи
    0.59
    Activations Density 0.009%

    No Known Activations