© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 156725
    Prev
    Next
    INDEX
    Explanations

    death of, rise to, satisfied as

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

    phrases to start tasks or questions

    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
     warriors
    0.47
     females
    0.45
     telenov
    0.44
     plas
    0.43
     VIS
    0.43
     nokta
    0.43
     త
    0.43
     Capítulo
    0.43
     blames
    0.42
     obnoxious
    0.42
    POSITIVE LOGITS
    Нор
    0.48
    Як
    0.45
    Доб
    0.43
    国有
    0.43
     учетом
    0.43
    浥
    0.42
    фон
    0.42
    Фе
    0.41
    ↵↵↵↵
    0.41
    同样
    0.41
    Activations Density 0.000%

    No Known Activations