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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99488
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
    金額
    -0.85
    Always
    -0.85
    Every
    -0.85
    Usually
    -0.83
     same
    -0.83
    Almost
    -0.81
    Another
    -0.80
    áska
    -0.79
    lenmiş
    -0.78
     routinely
    -0.77
    POSITIVE LOGITS
    >,
    1.02
    £
    0.93
    siah
    0.93
     bijvoorbeeld
    0.89
    ált
    0.89
    «
    0.88
    (),
    0.87
    €
    0.87
     Coordin
    0.87
    っていた
    0.87
    Activations Density 0.013%

    No Known Activations