© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59489
    Prev
    Next
    INDEX
    Explanations

    sentiment analysis

    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
     dentelle
    -0.78
    🎃
    -0.72
     Metropol
    -0.72
     Stron
    -0.71
    sweat
    -0.69
     doigt
    -0.69
    setP
    -0.69
     Seri
    -0.69
     METH
    -0.68
     قاشق
    -0.68
    POSITIVE LOGITS
     sentiment
    3.58
     Sentiment
    2.77
    sentiment
    2.63
    Sentiment
    2.63
     sentiments
    2.41
     Senti
    1.92
     sentimental
    1.91
     sentimiento
    1.81
    Senti
    1.78
    senti
    1.77
    Activations Density 0.063%

    No Known Activations