© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100610
    Prev
    Next
    INDEX
    Explanations

    parasites and xenografts

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

    plural noun endings, particularly scientific terms that end in "-ts" like "xenografts," "transplantation," and "agglomeration."

    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
     the
    -1.84
    0
    -1.67
     plusieurs
    -1.56
    に入って
    -1.55
    y
    -1.54
    ();
    -1.52
    Tetapi
    -1.49
     prendre
    -1.49
    1
    -1.49
    に行って
    -1.48
    POSITIVE LOGITS
     sebagainya
    1.58
     they
    1.52
    мне
    1.44
     if
    1.40
    terday
    1.38
    简称
    1.38
     useAppContext
    1.37
     there
    1.34
     🔥🔥
    1.34
     одна
    1.32
    Activations Density 0.271%

    No Known Activations