© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 86844
    Prev
    Next
    INDEX
    Explanations

    programming directives

    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_34/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
     kalem
    -0.89
    ají
    -0.84
    Norge
    -0.84
    agrad
    -0.81
    歩道
    -0.80
     but
    -0.79
     콘텐츠
    -0.78
    kyt
    -0.78
    Noter
    -0.78
    Fot
    -0.78
    POSITIVE LOGITS
    foreach
    1.44
    if
    1.39
    php
    1.14
    include
    1.11
     if
    1.00
    fore
    0.98
    for
    0.90
    isset
    0.85
     entgeg
    0.85
     include
    0.84
    Activations Density 0.003%

    No Known Activations