© 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. 10-GEMMASCOPE-RES-131K
    7. 725
    Prev
    Next
    INDEX
    Explanations

    variety and diversity

    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
    lhes
    -1.59
     Then
    -1.59
     Suom
    -1.55
     Probably
    -1.48
     time
    -1.47
     Ironically
    -1.45
    
    -1.44
    umenter
    -1.43
     ulter
    -1.43
     burbu
    -1.41
    POSITIVE LOGITS
     mít
    1.81
    ikusbot
    1.59
     vytvá
    1.54
    姽
    1.52
     και
    1.50
     sép
    1.50
     wherein
    1.48
     iArr
    1.47
    🢒
    1.46
    liehen
    1.45
    Activations Density 0.034%

    No Known Activations