© 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. 34789
    Prev
    Next
    INDEX
    Explanations

    logging framework usage

    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
     INFO
    -0.91
    INFO
    -0.88
     info
    -0.87
    RESP
    -0.80
     confiar
    -0.78
    ЙТЕ
    -0.77
    clable
    -0.77
    イエロー
    -0.77
    ようになります
    -0.76
    Info
    -0.75
    POSITIVE LOGITS
    category
    1.03
     category
    1.03
     categories
    0.89
     subcategory
    0.87
     at
    0.87
    bouw
    0.84
    Category
    0.82
    Prefix
    0.82
    ตั้ง
    0.82
    multer
    0.80
    Activations Density 0.027%

    No Known Activations