© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 8659
    Prev
    Next
    INDEX
    Explanations

    relatively

    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
     garanti
    1.95
    గు
    1.88
    ರ
    1.88
     devra
    1.87
     faudra
    1.86
     obtuvo
    1.80
     pré
    1.78
     fortement
    1.73
     waktu
    1.72
     eğer
    1.72
    POSITIVE LOGITS
    ه
    1.92
    ी
    1.84
    น
    1.75
    i
    1.73
    ians
    1.72
    ে
    1.66
    로운
    1.63
    iate
    1.59
    د
    1.57
    ้
    1.55
    Activations Density 0.037%

    No Known Activations