© 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. 22-GEMMASCOPE-RES-131K
    7. 14239
    Prev
    Next
    INDEX
    Explanations

    medical terms, body parts

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

    technical terms related to computing and technology, particularly those ending with suffixes like "base," "map," "drive," "match," "play," and "balance."

    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_22/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
    為に
    -2.05
    へ向
    -2.02
    に追加
    -1.89
    に入れる
    -1.89
    に入る
    -1.88
     and
    -1.88
     Of
    -1.85
    つづく
    -1.81
     '
    -1.80
     acorde
    -1.77
    POSITIVE LOGITS
    <bos>
    2.78
    もある
    2.11
    です
    2.08
    鈊
    2.05
    を
    2.02
     mily
    1.97
     kula
    1.95
    媄
    1.94
    では
    1.91
     endi
    1.91
    Activations Density 0.523%

    No Known Activations