© 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. 31-GEMMASCOPE-2-RES-262K
    7. 135116
    Prev
    Next
    INDEX
    Explanations

    volunteer project or skin barrier

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     האי
    0.49
     철
    0.45
     fillets
    0.44
     декора
    0.44
     தயாரிக்க
    0.44
     접
    0.41
    撗
    0.40
    鐵
    0.40
    obraz
    0.40
     Фила
    0.40
    POSITIVE LOGITS
     decisione
    0.60
    ものである
    0.51
    ন
    0.50
     ogn
    0.50
    ものです
    0.49
     juga
    0.46
    よね
    0.45
     unanimous
    0.45
     oppure
    0.45
     ones
    0.44
    Activations Density 0.003%

    No Known Activations