© 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. 38430
    Prev
    Next
    INDEX
    Explanations

    Japanese, Chinese, Indonesian, or Arabic

    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
    iness
    -1.09
     (!__
    -1.09
     the
    -1.01
    ↵↵
    -1.00
    ing
    -0.97
     your
    -0.96
     богат
    -0.94
    咦
    -0.92
    get
    -0.92
    找
    -0.91
    POSITIVE LOGITS
    neiden
    1.21
    鱂
    1.16
     (
    1.15
     (‘
    1.15
    と呼ばれる
    1.13
    ppings
    1.09
     می‌گو
    1.09
     (“
    1.09
    hever
    1.07
     maig
    1.07
    Activations Density 0.087%

    No Known Activations