© 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. 33004
    Prev
    Next
    INDEX
    Explanations

    Q: or limiting membrane

    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
    getShared
    -0.99
    jö
    -0.91
     Kondisi
    -0.89
    꽁
    -0.88
     আপ
    -0.86
    lija
    -0.85
    க்கும்
    -0.84
    스
    -0.84
     Hopefully
    -0.84
     versus
    -0.84
    POSITIVE LOGITS
    "}";
    1.02
    ⟶
    0.96
     изображение
    0.90
     govt
    0.87
     NCERT
    0.86
     devoid
    0.85
    LinkedHashMap
    0.84
    पाद
    0.84
    emplar
    0.83
     rendering
    0.82
    Activations Density 0.010%

    No Known Activations