© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15519
    Prev
    Next
    INDEX
    Explanations

    testing and analysis

    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_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
     Epistle
    0.66
    ясплат
    0.66
    ⅰ
    0.63
    荩
    0.61
    眷
    0.59
    िश्च
    0.59
    埜
    0.59
     Isot
    0.58
     आईएस
    0.56
    ilà
    0.56
    POSITIVE LOGITS
    ᐅ
    0.54
     Produkte
    0.54
     test
    0.52
     tests
    0.52
     tested
    0.52
     chosen
    0.50
     getest
    0.49
     performance
    0.48
     spray
    0.48
    produkte
    0.48
    Activations Density 0.003%

    No Known Activations