© 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. 10-GEMMASCOPE-RES-131K
    7. 105791
    Prev
    Next
    INDEX
    Explanations

    Victor followed by names

    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_10/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
    
    -2.61
    ኞ
    -2.45
    图为
    -2.44
     futurs
    -2.38
    点此
    -2.33
    gucig
    -2.31
     inadequacy
    -2.30
    鄠
    -2.25
     ихъ
    -2.25
    鱟
    -2.23
    POSITIVE LOGITS
    1
    3.28
     {
    3.00
    It
    2.97
    </i>
    2.88
     Then
    2.77
    2
    2.77
    ate
    2.72
    \
    2.66
    Of
    2.58
    That
    2.56
    Activations Density 0.002%

    No Known Activations