© 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. 107828
    Prev
    Next
    INDEX
    Explanations

    QR code scanning

    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
    Wan
    -0.84
    ไ
    -0.82
    籴
    -0.80
     funciones
    -0.80
    Mc
    -0.80
    Crystal
    -0.79
    Triple
    -0.77
    roman
    -0.77
    North
    -0.75
    Chelsea
    -0.75
    POSITIVE LOGITS
     QR
    2.89
    QR
    2.16
     qr
    2.06
     code
    1.98
    qr
    1.88
     codes
    1.87
    code
    1.73
     barcode
    1.73
    QRCode
    1.65
     código
    1.60
    Activations Density 0.020%

    No Known Activations