© 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. 103958
    Prev
    Next
    INDEX
    Explanations

    creating objects or 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
    薷
    -1.51
    鸱
    -1.48
    鹛
    -1.46
    妧
    -1.43
    屃
    -1.35
    做得
    -1.33
    橚
    -1.31
    赑
    -1.27
    気持ちを
    -1.25
    能在
    -1.24
    POSITIVE LOGITS
     create
    1.45
    OrUpdate
    1.43
    垕
    1.40
     havoc
    1.40
     Cremation
    1.34
     new
    1.34
    gemeester
    1.12
     вот
    1.11
     Creating
    1.10
    dė
    1.10
    Activations Density 0.057%

    No Known Activations