© 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. 172474
    Prev
    Next
    INDEX
    Explanations

    Aurora, weapon, ice, country, south

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

    waste Management

    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
     Religion
    0.48
     Funding
    0.48
    ná
    0.47
     Scrolling
    0.46
     কোথা
    0.45
    நாள்
    0.45
     Specialties
    0.45
    漬
    0.44
    Ссылка
    0.44
     Microphone
    0.44
    POSITIVE LOGITS
     gase
    0.51
     aurora
    0.50
     آزمایش
    0.49
    Aurora
    0.48
     화
    0.47
     operat
    0.47
     عشر
    0.47
     élevé
    0.46
     Aurora
    0.46
     fluidized
    0.45
    Activations Density 0.001%

    No Known Activations