© 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. 10731
    Prev
    Next
    INDEX
    Explanations

    historical sources

    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
     insulating
    0.53
    に応じて
    0.52
     antider
    0.50
     Provinc
    0.50
     싫
    0.50
    AIRE
    0.49
     Normandy
    0.49
     Dordrecht
    0.49
     Prussia
    0.47
    inesi
    0.47
    POSITIVE LOGITS
     crecer
    0.62
     pály
    0.62
     población
    0.59
    bis
    0.59
     دقی
    0.57
     група
    0.56
    誒
    0.56
     gruppo
    0.55
     curva
    0.55
    كور
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.