© 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. 40359
    Prev
    Next
    INDEX
    Explanations

    technical receiver context

    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
    1
    -2.97
    {
    -2.47
    5
    -2.34
    of
    -2.22
     來
    -2.19
    –
    -2.16
     WHILE
    -2.13
    ⧠
    -2.13
     ‚
    -2.11
    i
    -2.11
    POSITIVE LOGITS
    medriver
    2.66
    щал
    2.53
    籏
    2.52
    
    2.50
     diseñar
    2.50
    
    2.50
    鹟
    2.48
    мії
    2.41
    𝄆
    2.41
    はなく
    2.34
    Activations Density 0.009%

    No Known Activations