© 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. 32991
    Prev
    Next
    INDEX
    Explanations

    twenty

    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
    3
    -1.00
    ۳۰
    -0.90
     Poitiers
    -0.84
     Font
    -0.80
     Nazar
    -0.79
    手中
    -0.77
     Ronald
    -0.77
    factura
    -0.75
     Glaser
    -0.75
     Louise
    -0.74
    POSITIVE LOGITS
     Twentieth
    1.93
     twentieth
    1.92
     ۲۰
    1.77
     twenty
    1.74
     २०
    1.65
     Twenty
    1.61
     ২০
    1.60
    Twenty
    1.59
    二十
    1.54
     TWENTY
    1.45
    Activations Density 0.067%

    No Known Activations