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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45314
    Prev
    Next
    INDEX
    Explanations

    creator names

    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
     setCode
    -0.79
    traversal
    -0.77
     movie
    -0.76
     setObject
    -0.75
    institute
    -0.75
     Wiley
    -0.73
    letus
    -0.72
     poden
    -0.71
    Rarity
    -0.71
    printStackTrace
    -0.70
    POSITIVE LOGITS
     creator
    3.67
     created
    3.11
    creator
    3.05
     creators
    2.88
     Creator
    2.86
    Creator
    2.84
    Created
    2.78
    created
    2.61
     Created
    2.58
     созда
    2.53
    Activations Density 0.057%

    No Known Activations