© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 1366
    Prev
    Next
    INDEX
    Explanations

    fundamental, and often immutable

    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_65k_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
     is
    0.71
     and
    0.71
     as
    0.70
     that
    0.62
     Ку
    0.60
     tokamaks
    0.60
     Во
    0.59
     Χ
    0.58
     Лит
    0.58
    </h2>
    0.58
    POSITIVE LOGITS
    -
    0.79
    is
    0.77
    en
    0.75
    on
    0.73
    N
    0.71
    in
    0.70
    ار
    0.70
    os
    0.68
    ből
    0.67
    od
    0.66
    Activations Density 1.218%

    No Known Activations