© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64860
    Prev
    Next
    INDEX
    Explanations

    code snippets starting with quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    可惜
    -1.98
     to
    -1.92
    などを
    -1.87
    がありますが
    -1.84
     sowohl
    -1.81
     ۱۷
    -1.77
    があるので
    -1.73
     spô
    -1.73
    issé
    -1.70
     ۱۶
    -1.65
    POSITIVE LOGITS
    んですよね
    1.92
    Y
    1.86
    んですよ
    1.83
     них
    1.77
     focused
    1.75
        
    1.71
    B
    1.69
     we
    1.67
     help
    1.66
    ſelves
    1.66
    Activations Density 0.012%

    No Known Activations