© 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. 35560
    Prev
    Next
    INDEX
    Explanations

    numbers and outcomes mentioning place

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

    numbers and characters

    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
     रिक्वेस्ट
    0.51
     クリーム
    0.50
    ជន
    0.47
     abrió
    0.45
     ಸಾಕ
    0.45
    ピンク
    0.45
    淒
    0.44
    𒊑
    0.44
    絕對
    0.44
     CREAM
    0.44
    POSITIVE LOGITS
    vr
    0.41
    лығы
    0.40
    dehyde
    0.40
    kova
    0.39
    developer
    0.39
    жу
    0.39
    стве
    0.39
    ığ
    0.39
    }`
    0.38
    ığında
    0.38
    Activations Density 0.030%

    No Known Activations