© 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. 28721
    Prev
    Next
    INDEX
    Explanations

    introducing an explanation or opinion

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

    exclamatory follow-ups

    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
    malign
    0.49
    อ
    0.48
    会在
    0.47
    짧
    0.46
    Gc
    0.46
     पड़ेगा
    0.45
    Synchron
    0.45
     会
    0.45
    Sulf
    0.45
     Hydraul
    0.45
    POSITIVE LOGITS
    毕竟
    0.72
     hiszen
    0.62
     Ведь
    0.59
     ведь
    0.57
     unthinkable
    0.57
    だって
    0.57
     naprawdę
    0.55
     вполне
    0.55
    یا
    0.54
     навіть
    0.54
    Activations Density 0.037%

    No Known Activations