© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15220
    Prev
    Next
    INDEX
    Explanations

    linking clauses or ideas

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

    but introducing a contrast

    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_16k_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
    :
    0.62
    মাণের
    0.55
     can
    0.54
     in
    0.50
    !
    0.50
     বাসিন্দ
    0.49
     policym
    0.48
     నేపథ్యంలో
    0.48
     de
    0.47
     timeframe
    0.45
    POSITIVE LOGITS
    ，
    0.92
     ，
    0.73
     ,
    0.72
     ،
    0.70
    
    0.65
     ၊
    0.60
    ,【
    0.60
    রাষ্ট
    0.56
    ；
    0.56
    のですが
    0.55
    Activations Density 1.032%

    No Known Activations