© 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. 930
    Prev
    Next
    INDEX
    Explanations

    function definitions

    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
    他們
    -2.19
    </em>
    -1.98
                       
    -1.81
    ⍽
    -1.80
                            
    -1.77
    拶
    -1.77
    ௅
    -1.76
                
    -1.74
                          
    -1.73
    Should
    -1.73
    POSITIVE LOGITS
     in
    2.14
     even
    2.06
     when
    1.95
     with
    1.95
    {
    1.83
     apsau
    1.80
     after
    1.71
    덮
    1.70
     if
    1.70
     «
    1.68
    Activations Density 0.013%

    No Known Activations