© 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. 11640
    Prev
    Next
    INDEX
    Explanations

    great

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

    great combined with other words

    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
    م
    1.06
    리
    0.95
    ри
    0.95
    un
    0.94
    व
    0.93
    il
    0.89
    وم
    0.88
    m
    0.88
    ي
    0.83
    ou
    0.82
    POSITIVE LOGITS
     great
    1.04
    .
    0.97
     GREAT
    0.95
    great
    0.93
     Great
    0.79
     вели
    0.77
    GREAT
    0.76
     stride
    0.75
     I
    0.70
     grande
    0.69
    Activations Density 0.067%

    No Known Activations