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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109867
    Prev
    Next
    INDEX
    Explanations

    contextual qualifiers

    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_34/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
    طاء
    -0.91
    ليك
    -0.89
     walang
    -0.87
     György
    -0.82
    Romain
    -0.81
    Baik
    -0.81
     Romain
    -0.80
     yves
    -0.79
    ̚
    -0.78
     zis
    -0.77
    POSITIVE LOGITS
     Cincinnati
    0.92
     "..\..\
    0.91
     Brenner
    0.87
     Stadtteil
    0.86
    estimm
    0.85
     maniac
    0.85
              
    0.85
    aley
    0.84
                      
    0.84
    wohnung
    0.84
    Activations Density 0.001%

    No Known Activations