© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 40366
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ت
    0.96
    Edad
    0.95
    ะ
    0.93
     ദുൽ
    0.90
    ون
    0.87
    는
    0.86
    aar
    0.84
    ң
    0.84
     manzanas
    0.83
    ம்
    0.82
    POSITIVE LOGITS
     divers
    0.82
     gratitude
    0.82
     sens
    0.80
     irrepar
    0.80
     cens
    0.79
     restaur
    0.77
     eau
    0.77
     reimb
    0.77
     transgress
    0.77
     verwend
    0.76
    Activations Density 0.000%

    No Known Activations