© 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. 102949
    Prev
    Next
    INDEX
    Explanations

    messages, texts, labels

    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
     서
    -0.84
     помощью
    -0.69
     preparar
    -0.68
     that
    -0.67
     usługi
    -0.66
    他才
    -0.66
     try
    -0.66
    서는
    -0.66
     Breaking
    -0.66
     waits
    -0.66
    POSITIVE LOGITS
    messages
    1.15
    Validation
    1.04
    validation
    0.99
    merksamkeit
    0.90
     messages
    0.90
     sentences
    0.84
    wesen
    0.83
    QUI
    0.81
    UIM
    0.81
     texts
    0.80
    Activations Density 0.009%

    No Known Activations