© 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. 117914
    Prev
    Next
    INDEX
    Explanations

    SQL data type declarations

    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
     even
    -0.88
    高知
    -0.76
     before
    -0.74
    Even
    -0.73
     came
    -0.72
    éfonos
    -0.71
     Even
    -0.69
     Verbre
    -0.69
     showing
    -0.68
     regardless
    -0.68
    POSITIVE LOGITS
    CLR
    0.94
    ].[
    0.90
    ǂ
    0.89
     CLR
    0.87
     AS
    0.81
     fervent
    0.80
    )~
    0.79
    GO
    0.78
    XmlSchema
    0.78
     Wanneer
    0.77
    Activations Density 0.031%

    No Known Activations