© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 3606
    Prev
    Next
    INDEX
    Explanations

    activation, verification, approval, validation, job, isActive

    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
    Negative Logits
     –,
    0.61
     thiab
    0.59
    </h2>
    0.58
     ili
    0.58
     itd
    0.57
     investir
    0.55
     investi
    0.55
    િ
    0.54
     ή
    0.54
     baw
    0.54
    POSITIVE LOGITS
    de
    0.71
    да
    0.65
     on
    0.61
    les
    0.57
    las
    0.57
    as
    0.56
    ings
    0.56
    са
    0.55
    genes
    0.55
    ollen
    0.55
    Activations Density 0.149%

    No Known Activations