© 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. 109866
    Prev
    Next
    INDEX
    Explanations

    network routes

    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
     후
    -0.81
    侶
    -0.80
    圓
    -0.79
    ongiorno
    -0.77
    إنه
    -0.75
    brandt
    -0.75
     Brücke
    -0.74
    圆
    -0.73
    時半
    -0.73
     Nelly
    -0.73
    POSITIVE LOGITS
     network
    4.00
     networks
    3.33
    network
    3.22
    Network
    2.78
     Network
    2.72
     réseau
    2.72
     NETWORK
    2.70
    networks
    2.56
    网络
    2.50
    NETWORK
    2.41
    Activations Density 0.099%

    No Known Activations