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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7704
    Prev
    Next
    INDEX
    Explanations

    if not exists

    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
    upgrade
    -0.76
     Inclusion
    -0.75
    unwrap
    -0.75
    ందు
    -0.74
     unavailable
    -0.73
     interni
    -0.73
     Cuar
    -0.73
     Mejía
    -0.73
     congregations
    -0.72
     choisissez
    -0.72
    POSITIVE LOGITS
    exists
    0.87
     exists
    0.85
    entendre
    0.82
     hasattr
    0.81
     exist
    0.75
    lour
    0.74
    терапия
    0.73
    roughts
    0.71
    localisation
    0.71
    panda
    0.70
    Activations Density 0.006%

    No Known Activations