© 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. 44027
    Prev
    Next
    INDEX
    Explanations

    PHP programming contexts

    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
    {
    -3.70
     they
    -3.56
    al
    -3.23
     Wissenschaftler
    -3.14
     him
    -2.98
    を始め
    -2.80
    </strong>
    -2.58
    但我
    -2.44
     qualifié
    -2.42
    
    -2.42
    POSITIVE LOGITS
    s
    3.03
    For
    2.56
    B
    2.50
     They
    2.44
     炒め
    2.42
    To
    2.39
    So
    2.27
    Since
    2.19
    あります
    2.19
    there
    2.19
    Activations Density 0.016%

    No Known Activations