© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50372
    Prev
    Next
    INDEX
    Explanations

    redirect to url or path

    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
     increíbles
    -0.94
     Româ
    -0.90
     resolução
    -0.90
    עת
    -0.87
    至
    -0.84
     Enzymes
    -0.83
     impresionantes
    -0.82
    出てくる
    -0.82
     sống
    -0.82
    nili
    -0.82
    POSITIVE LOGITS
     with
    1.11
     after
    0.94
    Success
    0.90
    ugal
    0.89
     снова
    0.88
    tidig
    0.87
     because
    0.86
     Lauder
    0.86
    🏠
    0.82
     piso
    0.82
    Activations Density 0.004%

    No Known Activations