© 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. 22-GEMMASCOPE-RES-131K
    7. 35853
    Prev
    Next
    INDEX
    Explanations

    choose options and flexibility

    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_22/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
     when
    -1.00
    conomie
    -0.94
     cannot
    -0.91
    waniem
    -0.90
     in
    -0.89
    ))));
    -0.89
    千年
    -0.84
     during
    -0.82
    لها
    -0.80
    两个
    -0.78
    POSITIVE LOGITS
    可以选择
    1.55
    自由に
    1.52
     options
    1.48
     flexibility
    1.45
     flexible
    1.41
    choose
    1.41
     choices
    1.39
     modular
    1.34
     선택
    1.33
     dowol
    1.31
    Activations Density 0.127%

    No Known Activations