© 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. 118684
    Prev
    Next
    INDEX
    Explanations

    localhost addresses and ports

    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
    lining
    -0.75
     getStatus
    -0.73
     those
    -0.72
     слишком
    -0.71
     Prü
    -0.71
    ôle
    -0.71
     there
    -0.71
     Chinois
    -0.70
     setStatus
    -0.70
    resultSet
    -0.69
    POSITIVE LOGITS
     port
    1.23
     backend
    1.13
     PORT
    1.04
    mern
    1.01
    Backend
    0.97
     Backend
    0.95
     server
    0.95
     czter
    0.93
    herokuapp
    0.92
    Port
    0.90
    Activations Density 0.008%

    No Known Activations