© 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-262K
    7. 116089
    Prev
    Next
    INDEX
    Explanations

    nylon cloth or feet

    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
    Negative Logits
    dus
    0.59
    اد
    0.55
    albums
    0.54
    اع
    0.53
    arounds
    0.52
    sectors
    0.52
    d
    0.52
    ements
    0.51
    тура
    0.48
    ات
    0.48
    POSITIVE LOGITS
     reuni
    0.66
     dictator
    0.63
     Demonstr
    0.63
     transparente
    0.61
     produz
    0.61
     procedimento
    0.59
     制
    0.59
     Dali
    0.59
     Zariski
    0.59
     Frankenstein
    0.58
    Activations Density 0.001%

    No Known Activations