© 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. 22-GEMMASCOPE-RES-131K
    4. 13533
    Prev
    Next
    INDEX
    Explanations

    Hypo, OB

    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_22/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
     any
    -1.12
     “[
    -1.08
     each
    -1.02
     they
    -0.94
     leksikon
    -0.89
    balancer
    -0.87
    жным
    -0.86
     Bundesrepublik
    -0.86
    вети
    -0.86
     любого
    -0.85
    POSITIVE LOGITS
     gelegt
    1.07
     plagues
    0.96
    Bhar
    0.96
     empfangen
    0.96
    ヽ
    0.94
     communautés
    0.92
    ❼
    0.92
    śród
    0.92
     tých
    0.92
     manageable
    0.91
    Activations Density 0.001%

    No Known Activations