© 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. 12-GEMMASCOPE-2-RES-16K
    7. 9133
    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_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
    را
    2.78
    не
    2.73
    در
    2.45
    s
    2.27
    ма
    2.09
    h
    2.05
    م
    2.05
    á
    2.03
    ar
    1.98
    де
    1.96
    POSITIVE LOGITS
     loophole
    1.59
     وعلى
    1.58
    maßen
    1.57
     shove
    1.50
     particulières
    1.49
     teniendo
    1.42
     convincingly
    1.41
    Missense
    1.41
     cambiamenti
    1.41
    Lähteet
    1.41
    Activations Density 0.065%

    No Known Activations