© 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. 31-GEMMASCOPE-2-RES-16K
    7. 400
    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_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.41
     ಪ್ರಾರಂಭ
    0.35
     automaticamente
    0.34
    ります
    0.34
    くなります
    0.34
     vanligt
    0.33
     ಯಾವಾಗ
    0.32
    出来了
    0.32
    咦
    0.31
     আরম্ভ
    0.31
    POSITIVE LOGITS
     who
    1.02
    who
    0.87
     whose
    0.86
     الذين
    0.82
     quienes
    0.82
     जिन्होंने
    0.77
     whom
    0.76
    whose
    0.72
     vying
    0.72
     whos
    0.70
    Activations Density 3.266%

    No Known Activations