© 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. 90674
    Prev
    Next
    INDEX
    Explanations

    Fetching results or responses

    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
     but
    -1.02
     for
    -0.90
    Revel
    -0.86
     From
    -0.86
     Get
    -0.86
    ilí
    -0.86
    viš
    -0.83
     to
    -0.82
     Keep
    -0.81
     #
    -0.81
    POSITIVE LOGITS
     result
    2.05
     response
    1.97
     results
    1.82
    result
    1.62
     результат
    1.45
     rezultat
    1.45
    結果
    1.45
     responses
    1.42
    结果
    1.42
     resposta
    1.41
    Activations Density 0.008%

    No Known Activations