© 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. 228189
    Prev
    Next
    INDEX
    Explanations

    descriptive terms and specifications

    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
    طنين
    0.47
     கற்ப
    0.46
    腧
    0.45
    ♥♥
    0.43
     छवियों
    0.43
    促进
    0.43
    শিক্ষ
    0.42
    КИ
    0.42
     የተለያዩ
    0.42
    ผู้ชม
    0.41
    POSITIVE LOGITS
     mediterranean
    0.54
     miso
    0.54
     mediterr
    0.54
     chalet
    0.51
     hof
    0.50
     Aegean
    0.49
     congress
    0.48
     militar
    0.48
     p
    0.47
     at
    0.47
    Activations Density 0.001%

    No Known Activations