© 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-16K
    7. 11894
    Prev
    Next
    INDEX
    Explanations

    Marshal.SizeOf, bottomRight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-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
    Not in Any Lists

    No Comments

    Negative Logits
    ्स
    1.97
    ই
    1.92
    飧
    1.87
    ി
    1.80
    なります
    1.73
    히
    1.73
    ുമു
    1.70
     eigenvalue
    1.69
     inconceivable
    1.66
    o
    1.66
    POSITIVE LOGITS
    ą
    2.70
    ak
    2.67
    ę
    2.30
    ęs
    2.28
    ون
    2.13
    PAR
    2.06
    ata
    2.02
    ες
    1.98
    í
    1.96
    ana
    1.91
    Activations Density 0.011%

    No Known Activations