© 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. 31008
    Prev
    Next
    INDEX
    Explanations

    expressive sounds and greetings

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

    expressions of gratitude or congratulations

    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
    і
    0.49
    ิจ
    0.47
     있으며
    0.46
     אך
    0.45
    म
    0.44
    Nevertheless
    0.43
    ಣ
    0.43
     portrayal
    0.42
     ет
    0.42
    
    0.42
    POSITIVE LOGITS
     habíamos
    0.51
     wcześniej
    0.50
     Başkanı
    0.49
     congratulations
    0.47
     pouquinho
    0.47
     graças
    0.47
     ήταν
    0.46
     gracias
    0.45
     dzięki
    0.45
    上げた
    0.44
    Activations Density 0.000%

    No Known Activations