© 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. 250744
    Prev
    Next
    INDEX
    Explanations

    ticket booth

    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
    о
    0.55
     incorrect
    0.55
    т
    0.54
     estrell
    0.52
     drewn
    0.52
    ї
    0.50
     erroneous
    0.48
    ल
    0.48
    ו
    0.48
     certaines
    0.48
    POSITIVE LOGITS
    TRACE
    0.46
    ARP
    0.46
    pract
    0.46
    GFS
    0.45
     নিযুক্ত
    0.45
    CHAIN
    0.44
    WISE
    0.44
    science
    0.43
     Обычно
    0.43
    churn
    0.43
    Activations Density 0.001%

    No Known Activations