© 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. 102851
    Prev
    Next
    INDEX
    Explanations

    plant and blade descriptions

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

    scientific plant names and botanical terminology.

    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
     parcour
    -0.82
    DPA
    -0.73
    HttpGet
    -0.71
     طولانی
    -0.71
    श्
    -0.71
     Limoges
    -0.70
    шками
    -0.69
    采访
    -0.68
     Branch
    -0.67
    初代
    -0.66
    POSITIVE LOGITS
     sword
    1.30
     Sword
    1.09
    sword
    1.04
     swords
    0.94
    蕉
    0.91
     agave
    0.89
    劍
    0.89
     lily
    0.89
     Yuc
    0.88
     Blades
    0.86
    Activations Density 0.028%

    No Known Activations