© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159878
    Prev
    Next
    INDEX
    Explanations

    serve hot

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

    science and technology advancements

    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_262k_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
     наличи
    0.46
    令和
    0.45
    Quantidade
    0.45
    ombres
    0.45
    ના
    0.44
     गुर्जर
    0.44
     प्लेयर्स
    0.42
    奶
    0.42
     vayan
    0.42
    鸡
    0.42
    POSITIVE LOGITS
    
    0.54
     excellence
    0.46
    >∕
    0.46
     intravascular
    0.45
     explosive
    0.45
     ultraviolet
    0.43
     biotechnology
    0.43
     microarray
    0.43
     breakthroughs
    0.43
     geologic
    0.42
    Activations Density 0.001%

    No Known Activations