© 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. 80803
    Prev
    Next
    INDEX
    Explanations

    research and development efforts

    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
    管理员
    -0.98
    #+#
    -0.97
    mbal
    -0.95
    hebung
    -0.95
    现代
    -0.93
     formule
    -0.93
    統計
    -0.90
    льше
    -0.90
     حرفه
    -0.90
    决策
    -0.90
    POSITIVE LOGITS
     research
    2.16
     researchers
    1.63
     promising
    1.56
     development
    1.55
     breakthroughs
    1.52
     researching
    1.51
     advancements
    1.48
     testing
    1.45
    research
    1.45
     funding
    1.43
    Activations Density 0.107%

    No Known Activations