© 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. 78255
    Prev
    Next
    INDEX
    Explanations

    measure of quantity

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

    legal or conceptual phrases

    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
    Conversion
    0.47
    ĥ
    0.46
    į
    0.44
    ↵
    0.44
     conversion
    0.43
     डिस्ट्र
    0.42
     Afric
    0.42
    Eras
    0.42
     пото
    0.41
     יש
    0.41
    POSITIVE LOGITS
     მხოლოდ
    0.54
     শুধুমাত্র
    0.53
    多
    0.50
    اقة
    0.49
     schwierig
    0.46
     Nutzen
    0.46
    ａ
    0.46
     einfach
    0.45
     separable
    0.45
    多少
    0.45
    Activations Density 0.000%

    No Known Activations