© 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. 170137
    Prev
    Next
    INDEX
    Explanations

    opportunity, drink, site

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

    task unravels or begins

    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
     folyt
    0.46
    كمل
    0.45
     ر
    0.45
     vow
    0.44
     کامیاب
    0.43
     ت
    0.41
    د
    0.41
     wyp
    0.40
    ت
    0.40
    ز
    0.39
    POSITIVE LOGITS
    涉及到
    0.52
    過程中
    0.51
     inadvertently
    0.51
     과정
    0.49
     পর্যবেক্ষ
    0.48
     సందర్భంగా
    0.48
     sırasında
    0.47
    際に
    0.46
    过程中
    0.46
    চ্ছিলাম
    0.46
    Activations Density 0.168%

    No Known Activations