© 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. 200385
    Prev
    Next
    INDEX
    Explanations

    internet, websites, services

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

    words ending in "able" or common recipe/description terms

    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
    Q
    0.53
    8
    0.50
    That
    0.49
    ↵↵↵
    0.48
    Σ
    0.48
    <0xE3>
    0.46
    Patients
    0.46
    ↵↵
    0.46
    Nan
    0.46
    Request
    0.46
    POSITIVE LOGITS
     ተግባ
    0.59
     नमी
    0.55
     လုပ်
    0.51
     इंटरनेट
    0.50
     ಯಾವುದ
    0.50
     ทุก
    0.49
     важли
    0.49
     หนึ่ง
    0.48
     시설
    0.48
     ಕಾನೂ
    0.48
    Activations Density 0.001%

    No Known Activations