© 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. 108866
    Prev
    Next
    INDEX
    Explanations

    crystal growth and spreading

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific terms and concepts in academic physics and chemistry papers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    jadikan
    -0.72
     hầm
    -0.71
     împre
    -0.71
    SHIRE
    -0.68
    フォーマンス
    -0.67
     najbol
    -0.67
     mieszkańców
    -0.67
     Camin
    -0.67
    РЕ
    -0.65
    quea
    -0.64
    POSITIVE LOGITS
     growth
    1.40
     growing
    1.16
    growth
    1.15
     evolving
    1.07
     Growth
    1.06
     GROWTH
    1.05
    rowth
    1.04
    growing
    1.02
    Growth
    1.02
     advancing
    0.99
    Activations Density 0.066%

    No Known Activations