© 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. 203093
    Prev
    Next
    INDEX
    Explanations

    various meetings

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

    ancient landscapes

    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
     análisis
    0.42
     데이터를
    0.42
     되면
    0.42
     dữ
    0.42
     データ
    0.41
    >{</
    0.41
    েম্বরে
    0.41
    ิ่ง
    0.40
     ваше
    0.40
     datasheet
    0.40
    POSITIVE LOGITS
     venting
    0.46
     planks
    0.45
    k
    0.42
     other
    0.41
     old
    0.41
     hour
    0.41
     handcrafted
    0.41
     स्वर्
    0.41
     Kum
    0.41
     Fred
    0.41
    Activations Density 0.003%

    No Known Activations