© 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. 75230
    Prev
    Next
    INDEX
    Explanations

    rendered decision, APPELLANT, sport shooter

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

    The neuron detects domain-specific, multi-syllable technical nouns (e.g. “bats,” “transfer,” “towers,” “gas,” “nutrition,” “turnover,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     était
    -1.51
    螣
    -1.41
    𖧵
    -1.41
    𖣘
    -1.38
    rådet
    -1.36
    InputBorder
    -1.32
     joya
    -1.32
    คือ
    -1.31
     their
    -1.31
    ⍢
    -1.30
    POSITIVE LOGITS
     already
    1.76
    <h2>
    1.66
     only
    1.53
    Furthermore
    1.44
    If
    1.39
     currently
    1.34
    );
    1.34
     dirit
    1.33
    Also
    1.32
     permukaan
    1.31
    Activations Density 0.243%

    No Known Activations