© 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. 48144
    Prev
    Next
    INDEX
    Explanations

    SQL ADO statements record

    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
     Carlsbad
    -0.80
     mvc
    -0.77
     anteriormente
    -0.75
    ッキー
    -0.74
    SALT
    -0.73
    iecie
    -0.72
    ogar
    -0.72
    šak
    -0.71
     exud
    -0.70
    ルフ
    -0.69
    POSITIVE LOGITS
     record
    0.99
     Record
    0.96
    Record
    0.92
    邨
    0.88
     рекор
    0.85
    Fields
    0.82
     Season
    0.82
    Field
    0.78
    PageSize
    0.77
    レコード
    0.77
    Activations Density 0.023%

    No Known Activations