© 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. 10-GEMMASCOPE-RES-131K
    7. 99194
    Prev
    Next
    INDEX
    Explanations

    words starting with over

    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_10/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
     to
    -3.36
    P
    -1.98
     なら
    -1.92
    
    -1.88
    mpagne
    -1.85
    o
    -1.81
    ta
    -1.79
     produisent
    -1.78
    ➬
    -1.77
     mesta
    -1.77
    POSITIVE LOGITS
    
    2.44
    
    2.28
     ซึ่ง
    2.22
    8
    2.08
    ↵
    2.03
     Conferencia
    1.98
     Ngày
    1.96
     Pemain
    1.95
     pendaftaran
    1.95
     dikirim
    1.92
    Activations Density 0.010%

    No Known Activations