© 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. 10-GEMMASCOPE-RES-131K
    7. 86230
    Prev
    Next
    INDEX
    Explanations

    grass and hay

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

    references to grass or grass-like plants in environmental or botanical contexts.

    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_10/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
     these
    -1.54
    𓋼
    -1.45
    mathbb
    -1.38
    ется
    -1.36
     cheating
    -1.35
     isla
    -1.34
    ではでは
    -1.34
    тус
    -1.32
     broche
    -1.30
    簟
    -1.30
    POSITIVE LOGITS
     naszej
    1.54
    一般的
    1.53
     genellikle
    1.49
     naszego
    1.47
     haupts
    1.43
    fondos
    1.42
     який
    1.41
     angefangen
    1.40
     gespielt
    1.40
     strolled
    1.38
    Activations Density 0.029%

    No Known Activations