© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84512
    Prev
    Next
    INDEX
    Explanations

    items included or with

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of numeric values (quantities, measurements, prices, etc.) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
            
    -2.11
      
    -1.88
     "
    -1.71
     this
    -1.69
        
    -1.66
     .
    -1.65
                        
    -1.61
    ↵
    -1.60
              
    -1.60
    '
    -1.48
    POSITIVE LOGITS
     '</
    1.60
     ''
    1.56
    ☆☆☆☆
    1.55
    vermectin
    1.51
     醬
    1.48
     coute
    1.47
    llavero
    1.46
     strategie
    1.44
    ꯳
    1.43
    歺
    1.43
    Activations Density 0.055%

    No Known Activations