© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49841
    Prev
    Next
    INDEX
    Explanations

    ip addr add

    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
    bca
    -0.77
     toothpaste
    -0.76
    bq
    -0.76
     القوات
    -0.76
    自然是
    -0.73
    irp
    -0.72
    idste
    -0.70
     ớt
    -0.69
     postpon
    -0.69
     adapters
    -0.69
    POSITIVE LOGITS
     key
    0.93
     learn
    0.84
     remove
    0.82
     address
    0.82
     replenish
    0.78
     Address
    0.78
     щоб
    0.78
    key
    0.77
    configurable
    0.77
     teach
    0.77
    Activations Density 0.006%

    No Known Activations