© 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. 97942
    Prev
    Next
    INDEX
    Explanations

    president confirmation statement

    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
    اكل
    -0.94
     declaró
    -0.89
     Really
    -0.77
    능
    -0.77
    intenant
    -0.72
    éti
    -0.72
    솜
    -0.72
    走的
    -0.72
     sério
    -0.69
     stated
    -0.67
    POSITIVE LOGITS
    avail
    0.95
    স্ত
    0.93
    ateur
    0.90
    ný
    0.89
    ließlich
    0.87
     Assessments
    0.87
    jamientos
    0.85
     البته
    0.84
    essment
    0.84
     conveyed
    0.84
    Activations Density 0.004%

    No Known Activations