© 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. 9256
    Prev
    Next
    INDEX
    Explanations

    mathematical rearrangements and series

    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
    </i>
    -1.73
     cepillo
    -1.61
     BECAUSE
    -1.56
     who
    -1.55
     этих
    -1.46
    
    -1.41
     jLabel
    -1.41
     потому
    -1.40
    を使って
    -1.38
    訁
    -1.38
    POSITIVE LOGITS
     at
    2.28
     from
    2.22
     then
    2.00
     to
    1.95
     the
    1.92
     all
    1.88
     it
    1.70
     four
    1.45
     before
    1.44
     nestled
    1.41
    Activations Density 0.063%

    No Known Activations