© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 500
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     erred
    0.99
    giene
    0.99
     workpiece
    0.94
     labore
    0.92
    idual
    0.91
     باتوں
    0.89
     borrows
    0.89
     déchets
    0.88
     workmanship
    0.87
    )/
    0.86
    POSITIVE LOGITS
     더욱
    1.79
     become
    1.66
     convertirse
    1.63
    更加
    1.57
     increasingly
    1.56
     becoming
    1.54
     diventare
    1.52
    更为
    1.47
     menjadi
    1.46
     훨씬
    1.46
    Activations Density 7.229%

    No Known Activations