© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108614
    Prev
    Next
    INDEX
    Explanations

    find document

    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
    <mask>
    -0.75
    
    -0.71
    benzyl
    -0.69
    lovak
    -0.67
    겹
    -0.66
     appContext
    -0.65
    苗
    -0.65
     huh
    -0.63
     while
    -0.63
    州
    -0.63
    POSITIVE LOGITS
     document
    3.53
     documents
    3.44
    document
    2.98
    Document
    2.81
     Document
    2.75
     Documents
    2.67
    documents
    2.64
     documentos
    2.59
    Documents
    2.52
     doc
    2.41
    Activations Density 0.062%

    No Known Activations