© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74696
    Prev
    Next
    INDEX
    Explanations

    returning web responses

    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
     anderen
    -1.87
    selbe
    -1.80
     gier
    -1.62
     ekip
    -1.57
    其他的
    -1.55
     andere
    -1.52
     weiterer
    -1.52
     other
    -1.50
    
    -1.49
     andern
    -1.47
    POSITIVE LOGITS
    袮
    1.81
    While
    1.59
    With
    1.54
    ductors
    1.46
     despite
    1.42
     comand
    1.41
    群馬
    1.40
    Despite
    1.38
    ementara
    1.36
    あなたは
    1.34
    Activations Density 0.003%

    No Known Activations