© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11304
    Prev
    Next
    INDEX
    Explanations

    « or » followed by a word

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

    The neuron detects numeric citation or reference markers (numbers, often with decimals) enclosed in angle‐quote punctuation.

    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
    0
    -3.03
    ៚
    -2.61
     synergies
    -2.44
     distaste
    -2.41
     sonrası
    -2.38
     estábamos
    -2.38
     them
    -2.36
     große
    -2.34
     französische
    -2.33
    ではまた
    -2.30
    POSITIVE LOGITS
     they
    3.45
    ],
    2.67
     But
    2.63
    ,”
    2.61
    ຼ
    2.41
    м
    2.33
    );
    2.31
    .";
    2.30
    k
    2.28
    )$
    2.27
    Activations Density 0.003%

    No Known Activations