© 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. 163736
    Prev
    Next
    INDEX
    Explanations

    welcomed morning, agrees

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

    historical context and change

    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
    ване
    0.52
    та
    0.43
    מן
    0.43
    🖕
    0.43
    👖
    0.43
     సి
    0.42
    ті
    0.42
    []);
    0.42
     مقرر
    0.42
    แมนเชสเตอร์ซิตี
    0.42
    POSITIVE LOGITS
     structures
    0.50
     interpretive
    0.49
     آسی
    0.46
    Message
    0.45
     architecture
    0.43
     message
    0.43
     lysine
    0.43
     ngũ
    0.43
     või
    0.42
     ویس
    0.42
    Activations Density 0.000%

    No Known Activations