© 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. 34-GEMMASCOPE-RES-131K
    4. 33046
    Prev
    Next
    INDEX
    Explanations

    access to exclusive features

    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
    ihnachts
    -1.05
    ihnachten
    -0.97
    ୀ
    -0.94
    龕
    -0.92
    ệm
    -0.92
    värr
    -0.91
    تمبر
    -0.88
    исленность
    -0.85
    gelijke
    -0.84
    apture
    -0.84
    POSITIVE LOGITS
     exclusive
    2.50
     priority
    2.09
     access
    1.98
    exclusive
    1.94
    Exclusive
    1.77
     discounts
    1.70
    priority
    1.69
    Priority
    1.63
     Exclusive
    1.51
    access
    1.48
    Activations Density 0.056%

    No Known Activations