© 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. 222458
    Prev
    Next
    INDEX
    Explanations

    appoints or last updated

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

    latest blog post offering leadership

    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
    ğimiz
    0.46
     CAP
    0.45
    ली
    0.45
    à
    0.44
     tecnológico
    0.43
     ني
    0.43
    SuppressWarnings
    0.43
    ̀ng
    0.43
     deniz
    0.43
    ebay
    0.43
    POSITIVE LOGITS
     appoint
    0.49
    掉了
    0.47
    没办法
    0.46
     appoints
    0.45
    둬
    0.45
    gående
    0.43
    ب
    0.43
     Montoya
    0.42
     아무
    0.42
    খাস্ত
    0.42
    Activations Density 0.001%

    No Known Activations