© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1090
    Prev
    Next
    INDEX
    Explanations

    referred to words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_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
     Old
    0.25
    Old
    0.24
    ാ
    0.24
    かなり
    0.24
    Volkswagen
    0.23
    Thermo
    0.23
    <0xBF>
    0.23
    JavaScript
    0.23
    <0xB5>
    0.22
    बहुत
    0.22
    POSITIVE LOGITS
     aforementioned
    0.30
     tersebut
    0.29
     مذکور
    0.28
     उक्त
    0.27
    ansir
    0.26
     leps
    0.24
     algal
    0.24
     jeweil
    0.24
     উক্ত
    0.24
     dây
    0.23
    Activations Density 2.688%

    No Known Activations