© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83841
    Prev
    Next
    INDEX
    Explanations

    connects to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ประจํา
    0.57
    
    0.55
    GALAD
    0.54
    prestations
    0.54
    
    0.53
    єр
    0.52
    SrvGroup
    0.52
     архів
    0.52
    ᆼ
    0.51
    Digit
    0.50
    POSITIVE LOGITS
     –
    0.48
     but
    0.48
     y
    0.46
     false
    0.46
     TV
    0.46
    ↵↵
    0.46
     R
    0.46
     Red
    0.44
     “
    0.44
     x
    0.44
    Activations Density 0.003%

    No Known Activations