© 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. 10-GEMMASCOPE-RES-131K
    7. 130804
    Prev
    Next
    INDEX
    Explanations

    karyometry

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers followed by underscores in programming code or technical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     with
    -1.74
     attain
    -1.55
     aktuellen
    -1.48
     If
    -1.48
     neuen
    -1.46
    ників
    -1.41
     aplicar
    -1.41
     mettez
    -1.38
     through
    -1.38
     encontram
    -1.38
    POSITIVE LOGITS
    
    1.54
    previously
    1.45
     fides
    1.45
    -
    1.37
    probably
    1.37
     –
    1.34
     xxii
    1.34
    e
    1.32
    wouldn
    1.32
     czerwca
    1.32
    Activations Density 0.008%

    No Known Activations