Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11636
    Prev
    Next
    INDEX
    Explanations

    parts of things that have connectors

    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_22/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
    			
    -1.48
     more
    -1.41
     both
    -1.41
     new
    -1.40
    j
    -1.37
    b
    -1.34
     being
    -1.31
          
    -1.28
     conosce
    -1.26
     after
    -1.24
    POSITIVE LOGITS
     that
    2.75
     which
    2.44
     که
    1.97
     που
    1.94
     whose
    1.77
     花朵
    1.73
     tirs
    1.70
    🔙
    1.69
     whoſe
    1.69
     who
    1.64
    Activations Density 0.326%

    No Known Activations