© 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. 4802
    Prev
    Next
    INDEX
    Explanations

    data collection and dangerous stunts

    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
    Coronavirus
    0.50
     πραγμα
    0.46
     reserve
    0.46
    Veget
    0.45
    贅
    0.44
    Reserve
    0.44
    corona
    0.43
    andia
    0.43
    森林
    0.43
     সিগারেট
    0.43
    POSITIVE LOGITS
     ana
    0.54
     wes
    0.54
     creó
    0.53
     in
    0.53
     বাদী
    0.52
     deu
    0.52
    _='
    0.50
    জনে
    0.50
     bez
    0.50
     Hana
    0.50
    Activations Density 0.000%

    No Known Activations