© 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. 124914
    Prev
    Next
    INDEX
    Explanations

    cheese, DIY, manufactured, Samuel, Muhammad

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

    technical terms and jargon

    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
     seda
    0.45
     orchestration
    0.44
     置
    0.43
     atof
    0.41
     perspici
    0.41
     undermine
    0.41
     dock
    0.40
     परे
    0.40
     ángulo
    0.40
     vía
    0.40
    POSITIVE LOGITS
     क्षमता
    0.45
    اجة
    0.44
     выбирать
    0.43
    人民
    0.43
    Cheese
    0.42
    🐞
    0.42
     मुस्लिम
    0.42
     عارف
    0.42
    Samuel
    0.42
    Muhammad
    0.41
    Activations Density 0.000%

    No Known Activations