© 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. 16-GEMMASCOPE-2-RES-262K
    7. 34939
    Prev
    Next
    INDEX
    Explanations

    array dimensions or sizes

    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
     class
    0.64
    ز
    0.64
    р
    0.64
     string
    0.63
     voiced
    0.63
     belief
    0.62
    т
    0.61
    ش
    0.59
     were
    0.58
     competency
    0.58
    POSITIVE LOGITS
    in
    0.83
     Suède
    0.75
    perhaps
    0.74
    raham
    0.71
    ıdır
    0.70
    iduría
    0.69
    fö
    0.68
    gegevens
    0.68
    aadhar
    0.66
    aldb
    0.66
    Activations Density 0.001%

    No Known Activations