© 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. 32769
    Prev
    Next
    INDEX
    Explanations

    very positive modifiers

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

    medical issues and questions

    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
    メソッド
    0.49
     सत्ता
    0.46
    搭载
    0.46
    ግዳ
    0.46
    ্ষিকী
    0.44
    觎
    0.43
     экземпля
    0.42
    🖕
    0.42
     merch
    0.42
     reportedly
    0.42
    POSITIVE LOGITS
     very
    0.62
     VERY
    0.60
     очень
    0.57
     bardzo
    0.57
     nagyon
    0.56
     wonderful
    0.55
     дуже
    0.55
     Ihrem
    0.55
     velmi
    0.54
     아주
    0.54
    Activations Density 0.184%

    No Known Activations