© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199661
    Prev
    Next
    INDEX
    Explanations

    explanation or definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ط
    0.55
     officielles
    0.49
    وا
    0.49
     dupla
    0.47
    新冠
    0.47
    ്രീ
    0.47
    ሪያ
    0.46
    远的
    0.46
    Arvore
    0.46
    Array
    0.45
    POSITIVE LOGITS
     начина
    0.59
     if
    0.57
     e
    0.49
     начинается
    0.49
    ;
    0.48
    ;;
    0.47
     pri
    0.46
     Waldorf
    0.46
    ];
    0.45
     если
    0.45
    Activations Density 0.008%

    No Known Activations