© 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. 75191
    Prev
    Next
    INDEX
    Explanations

    book formats

    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_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
     are
    -1.70
    禟
    -1.62
     offizielle
    -1.58
    鹩
    -1.55
    
    -1.55
    alties
    -1.53
    sowie
    -1.48
    Uhr
    -1.48
    榭
    -1.48
    beim
    -1.47
    POSITIVE LOGITS
    ?”
    2.13
    i
    2.06
    Contrary
    1.92
    a
    1.89
    ”;
    1.86
    𓆜
    1.86
    We
    1.85
    Despite
    1.80
    姘
    1.77
    In
    1.77
    Activations Density 0.004%

    No Known Activations