© 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. 63921
    Prev
    Next
    INDEX
    Explanations

    Sparkling Wine

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

    punctuation and specific roles

    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
     يستخدم
    0.55
    蜕
    0.54
    ˒
    0.50
     controla
    0.50
     lepro
    0.50
     transforme
    0.49
     použív
    0.49
     изображения
    0.49
     creando
    0.49
     industrie
    0.49
    POSITIVE LOGITS
    陸
    0.45
     Decatur
    0.45
    ็จ
    0.44
    決
    0.42
    目录下
    0.42
    歸
    0.41
    ਝ
    0.41
    大
    0.40
    归
    0.40
    Ҫ
    0.40
    Activations Density 0.000%

    No Known Activations