© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15961
    Prev
    Next
    INDEX
    Explanations

    coined from Sanskrit

    np_acts-logits-general · gemini-2.5-flash-lite

    code blocks or configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
     afili
    0.42
    álu
    0.41
     EUA
    0.40
    드로
    0.39
    '&
    0.39
     rad
    0.38
    '.'
    0.38
     successivamente
    0.38
    '){
    0.38
    ximation
    0.38
    POSITIVE LOGITS
     风
    0.50
     Eink
    0.41
    Verm
    0.41
     прав
    0.40
    斯拉
    0.40
    Dumper
    0.40
    传来
    0.40
     Кры
    0.39
    传承
    0.39
    的风
    0.39
    Activations Density 0.018%

    No Known Activations