© 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. 98858
    Prev
    Next
    INDEX
    Explanations

    preformatted text tag

    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
     TestCase
    -0.84
    ویس
    -0.81
    IUM
    -0.76
    🚸
    -0.76
    ulur
    -0.76
     venons
    -0.75
    uhkan
    -0.75
    inj
    -0.75
    බ
    -0.75
     aftermarket
    -0.73
    POSITIVE LOGITS
     pre
    4.25
    pre
    3.23
    Pre
    2.92
     Pre
    2.89
     PRE
    2.34
    PRE
    2.05
    before
    1.96
     قبل
    1.91
     sebelum
    1.91
     before
    1.84
    Activations Density 0.038%

    No Known Activations