© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15665
    Prev
    Next
    INDEX
    Explanations

    comparison or falsehood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     actually
    0.83
     heterogeneous
    0.82
     continental
    0.82
    м
    0.81
    за
    0.80
     savon
    0.80
    ased
    0.79
    viene
    0.79
     зимо
    0.78
    над
    0.78
    POSITIVE LOGITS
     운동
    1.21
     malam
    1.14
    pengaruhi
    1.11
     पोलियो
    1.11
     اتارنا
    1.10
     루
    1.10
     거고
    1.08
    운동
    1.07
    ايا
    1.07
     dini
    1.07
    Activations Density 0.000%

    No Known Activations