© 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. 15766
    Prev
    Next
    INDEX
    Explanations

    xml vs custom tag

    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
     Ili
    0.58
     bhar
    0.55
     ۵
    0.54
     bahwa
    0.54
     Zust
    0.53
     ziehen
    0.53
     genealog
    0.53
     dhamm
    0.53
     Prior
    0.53
     أنّ
    0.53
    POSITIVE LOGITS
     સૂ
    0.61
    decimals
    0.57
    TextArea
    0.57
    rint
    0.55
    ミュニ
    0.54
    咧
    0.54
    mtext
    0.52
    汇总
    0.52
    слу
    0.51
    }$(
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.