© 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. 199759
    Prev
    Next
    INDEX
    Explanations

    home and dumpster business

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

    anticipates threat or consequence

    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
     മറ
    0.48
    4
    0.47
    我们可以
    0.46
     ሌሎች
    0.46
    飞
    0.45
     sayesinde
    0.45
    hexane
    0.44
     متحدہ
    0.44
    ف
    0.43
    enabled
    0.43
    POSITIVE LOGITS
     disparity
    0.54
     acidosis
    0.46
     GA
    0.45
     discrepancy
    0.45
    稦
    0.45
     disparities
    0.43
    marginY
    0.43
     morbidity
    0.42
     fervor
    0.42
     SGA
    0.41
    Activations Density 0.001%

    No Known Activations