© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109844
    Prev
    Next
    INDEX
    Explanations

    code structures and networking

    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
    գ
    -0.79
     economy
    -0.69
    orneys
    -0.68
    Occasionally
    -0.68
    getPath
    -0.68
     molecular
    -0.68
    raham
    -0.68
     забо
    -0.67
    wnia
    -0.66
    Dtor
    -0.66
    POSITIVE LOGITS
     sockaddr
    1.13
    结构
    1.05
     structures
    0.94
     structure
    0.91
     струк
    0.85
     pulgadas
    0.83
     estrut
    0.82
     their
    0.82
     STRUCTURES
    0.81
    構造
    0.81
    Activations Density 0.054%

    No Known Activations