© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 261284
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     passcode
    0.52
     menyaksikan
    0.50
     doloribus
    0.49
    꽤
    0.48
     berkata
    0.46
     kaleidos
    0.46
     sebenarnya
    0.46
     quartzite
    0.45
    Due
    0.45
    Did
    0.45
    POSITIVE LOGITS
    krieg
    0.51
     खिलाड़ियों
    0.48
     खिलाड़ी
    0.48
    |,
    0.48
    ation
    0.47
    ational
    0.46
    ringing
    0.46
    marker
    0.46
    ding
    0.45
    forder
    0.44
    Activations Density 0.000%

    No Known Activations