© 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. 12300
    Prev
    Next
    INDEX
    Explanations

    many people

    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
    ’
    0.66
    مانی
    0.50
     imagery
    0.48
     evidence
    0.48
     or
    0.46
     signage
    0.46
     is
    0.45
    मा
    0.45
     néhány
    0.45
    Ж
    0.45
    POSITIVE LOGITS
     многих
    0.69
     людей
    0.68
     Menschen
    0.62
     многие
    0.61
     dintre
    0.61
     многи
    0.59
     Viele
    0.57
     বেশী
    0.57
     MANY
    0.57
     people
    0.56
    Activations Density 0.017%

    No Known Activations