Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8233
    Prev
    Next
    INDEX
    Explanations

    establishment and connection

    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
    printStackTrace
    -0.81
    показания
    -0.78
    ショップ
    -0.77
    udsman
    -0.77
    
    -0.74
     recoil
    -0.72
     networked
    -0.72
    itoral
    -0.71
     universal
    -0.71
    tagens
    -0.71
    POSITIVE LOGITS
     establish
    1.62
     ESTABL
    1.59
     establishment
    1.59
     established
    1.57
    establish
    1.55
     Establishment
    1.48
     establishing
    1.47
     Establish
    1.45
    Establish
    1.44
    establishment
    1.42
    Activations Density 0.094%

    No Known Activations