© 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. 49930
    Prev
    Next
    INDEX
    Explanations

    Zentangles technology, French Blue, agency Weiden, Family seeks

    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
    kose
    -0.97
     stenosis
    -0.88
    сылка
    -0.84
    tova
    -0.82
    glą
    -0.80
    urgence
    -0.78
     seguimiento
    -0.78
    ológia
    -0.78
    cauc
    -0.77
     Hydration
    -0.77
    POSITIVE LOGITS
     branding
    1.02
     wrapping
    0.89
     heel
    0.85
    branding
    0.84
     آموز
    0.79
     traditional
    0.77
     Ellsworth
    0.76
     Gedanke
    0.75
     branded
    0.75
     contrast
    0.73
    Activations Density 0.004%

    No Known Activations