© 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. 21281
    Prev
    Next
    INDEX
    Explanations

    accept mercy or forgiveness

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

    US leading, While Georgia, US economy

    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
     ∂
    0.41
     वग
    0.41
     abol
    0.41
     demonstrations
    0.41
     bodice
    0.41
     abolition
    0.41
    ότη
    0.41
     χρή
    0.41
     chu
    0.40
     RTL
    0.40
    POSITIVE LOGITS
    ergic
    0.44
    ury
    0.42
    ora
    0.42
    巖
    0.42
    calendar
    0.42
    stru
    0.41
    erra
    0.41
    tingham
    0.41
    ategoria
    0.41
    datum
    0.41
    Activations Density 0.000%

    No Known Activations