© 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. 82342
    Prev
    Next
    INDEX
    Explanations

    not followed by various states

    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
     not
    -2.73
     não
    -2.00
     Não
    -1.70
    ícias
    -1.70
     nicht
    -1.67
     tidak
    -1.48
    
    -1.47
     ikke
    -1.46
    Berdasarkan
    -1.45
    ไม่
    -1.45
    POSITIVE LOGITS
     only
    2.22
     только
    1.98
    Only
    1.94
     even
    1.86
    Even
    1.66
    only
    1.59
     Only
    1.38
     r
    1.34
     siquiera
    1.34
    t
    1.34
    Activations Density 0.100%

    No Known Activations