© 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. 115759
    Prev
    Next
    INDEX
    Explanations

    word collocations

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

    conflict and negative situations

    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
    菲
    0.47
    液
    0.47
    لف
    0.44
    銨
    0.44
    合金
    0.44
     لت
    0.43
    惠
    0.43
    (
    0.43
    $+
    0.43
    
    0.42
    POSITIVE LOGITS
     escreveu
    0.56
     fwrite
    0.50
     belir
    0.47
     escrever
    0.47
     धम
    0.44
     seguida
    0.44
    ริ่ม
    0.44
     फ्रेंड्स
    0.43
     hostility
    0.43
     ço
    0.43
    Activations Density 0.002%

    No Known Activations