© 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. 40679
    Prev
    Next
    INDEX
    Explanations

    herbivore, carnivore, omnivore

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

    terms describing animal dietary classifications such as "herbivore," "carnivore," "omnivore," and "insectivore."

    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
    絎
    -1.88
    随即
    -1.87
     撮っ
    -1.84
    𝑨
    -1.80
     apolog
    -1.78
    艄
    -1.73
    鋨
    -1.73
    which
    -1.73
     Produit
    -1.72
    لة
    -1.69
    POSITIVE LOGITS
     extraordinaire
    1.98
    .
    1.92
     ถ้า
    1.91
     It
    1.83
    激烈
    1.82
     Here
    1.76
    豺
    1.73
     теми
    1.73
    five
    1.70
    "
    1.69
    Activations Density 0.012%

    No Known Activations