© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34585
    Prev
    Next
    INDEX
    Explanations

    updating formulas and rules

    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
    InitialState
    -0.97
    Initial
    -0.96
    init
    -0.87
     iniz
    -0.87
    freopen
    -0.87
    initial
    -0.85
     början
    -0.85
     initially
    -0.85
     CONSTANT
    -0.83
    Inicial
    -0.82
    POSITIVE LOGITS
     update
    2.55
     updates
    2.25
     updating
    2.11
     Update
    2.03
    更新
    1.96
    update
    1.95
    Update
    1.89
     更新
    1.80
     updated
    1.73
     Updating
    1.70
    Activations Density 0.017%

    No Known Activations