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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10849
    Prev
    Next
    INDEX
    Explanations

    java and python dataclasses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '-'
    0.63
     aHUS
    0.63
     caster
    0.62
     पढ़ी
    0.62
     wu
    0.59
    вався
    0.57
     inexplicable
    0.57
     ಮಾರ್
    0.57
     '-
    0.57
     raisins
    0.56
    POSITIVE LOGITS
     @
    0.66
    @
    0.62
    Network
    0.57
    Duck
    0.55
    Generation
    0.54
    Nem
    0.52
    Azure
    0.51
    Like
    0.50
     Nem
    0.50
    〇
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.