© 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. 28000
    Prev
    Next
    INDEX
    Explanations

    Expression of

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

    numeric values, particularly when appearing in sequences with spaces and decimal points.

    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_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
     Início
    -1.09
     Acerca
    -1.02
    jadikan
    -1.02
     giyim
    -1.02
    quería
    -1.00
    ୈ
    -1.00
     by
    -0.99
    日から
    -0.98
     Itália
    -0.98
    でございます
    -0.97
    POSITIVE LOGITS
     outlier
    1.12
    oczes
    1.04
    atee
    1.03
    ragalactic
    1.00
    tissa
    0.99
    広く
    0.98
    ój
    0.97
     carrière
    0.94
     {};
    
    0.93
     vorgestellt
    0.92
    Activations Density 0.000%

    No Known Activations