© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1689
    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
     сотрудник
    0.64
     personne
    0.63
     MINISTER
    0.62
     compagnies
    0.58
    rict
    0.57
     osoba
    0.56
     osobe
    0.55
    !='')
    0.55
    회사
    0.54
    owner
    0.54
    POSITIVE LOGITS
     Reds
    0.86
     Wolverines
    0.81
     Panthers
    0.79
     Wildcats
    0.79
     Blues
    0.77
     Italians
    0.77
     Bobcats
    0.76
     Bulldogs
    0.75
     Trojans
    0.75
     boys
    0.74
    Activations Density 0.074%

    No Known Activations