© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72877
    Prev
    Next
    INDEX
    Explanations

    patch-clamp technique

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

    words or phrases that appear in technical or academic content.

    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
     and
    -1.63
     is
    -1.36
     will
    -1.34
    What
    -1.28
    Each
    -1.25
    <eos>
    -1.24
    这样的
    -1.22
    such
    -1.17
    옵
    -1.14
    可
    -1.13
    POSITIVE LOGITS
     about
    1.70
     again
    1.44
     one
    1.37
     atriz
    1.34
    んや
    1.32
    他们是
    1.31
    škoda
    1.31
    玏
    1.30
    一个是
    1.27
    ǵ
    1.26
    Activations Density 0.269%

    No Known Activations