© 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. 100665
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases

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

    technical or domain-specific terminology in formal/specialized contexts like code, legal, medical, or scientific documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on isolated, capitalized or title‐style single words (often technical labels, section headings, or proper nouns) in the text.

    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
     llamo
    -1.65
    !"
    -1.54
    𖧵
    -1.49
     ="
    -1.47
     bodyParser
    -1.44
    ᯾
    -1.42
    撻
    -1.41
     niitä
    -1.40
     péché
    -1.39
    </h1>
    -1.37
    POSITIVE LOGITS
     to
    1.72
    .
    1.48
    ESTAMP
    1.31
     literaria
    1.30
     サイト
    1.27
     Уже
    1.24
     动物
    1.23
    Typically
    1.22
    It
    1.20
    这个世界
    1.20
    Activations Density 0.000%

    No Known Activations