© 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. 109766
    Prev
    Next
    INDEX
    Explanations

    templating expressions

    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
    aconda
    -0.98
    tiglie
    -0.96
    abbix
    -0.95
     вещь
    -0.94
     prefeitura
    -0.93
    
    -0.93
     estampada
    -0.93
    стоит
    -0.92
    <0xF2>
    -0.92
    各种
    -0.92
    POSITIVE LOGITS
    uc
    0.95
     индивиду
    0.94
    ties
    0.91
     intolerable
    0.91
    ểm
    0.91
    loop
    0.90
     implode
    0.89
    穿搭
    0.89
     обстоя
    0.88
     ordinaria
    0.88
    Activations Density 0.010%

    No Known Activations