© 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. 7780
    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
     basic
    0.68
    uz
    0.67
     specific
    0.64
    oi
    0.62
    #!/
    0.61
     era
    0.59
     важли
    0.59
     men
    0.58
     plata
    0.57
    І
    0.57
    POSITIVE LOGITS
     analisar
    0.85
     tiveram
    0.85
    рное
    0.84
     oferecer
    0.79
     incrementar
    0.79
    atherine
    0.77
     Itália
    0.77
     Assad
    0.77
     написать
    0.76
    ÇÃO
    0.76
    Activations Density 0.000%

    No Known Activations