© 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. 16-GEMMASCOPE-2-RES-262K
    7. 119077
    Prev
    Next
    INDEX
    Explanations

    effect and impact

    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_16_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
    um
    1.27
    ת
    0.98
    im
    0.78
    ation
    0.75
    uu
    0.73
    en
    0.70
    os
    0.70
    in
    0.68
    ur
    0.67
    aw
    0.67
    POSITIVE LOGITS
    К
    0.80
    лә
    0.73
     казни
    0.73
     Не
    0.71
     affidavits
    0.71
     игр
    0.71
    MeToo
    0.69
     unworthy
    0.67
     aggrav
    0.66
     Ва
    0.66
    Activations Density 0.009%

    No Known Activations