© 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. 41723
    Prev
    Next
    INDEX
    Explanations

    scientific identifiers

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

    document ID numbers in academic or technical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on individual numeric characters, effectively spotting digits wherever they appear in the text (e.g. in citations, data values, or section numbers).

    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
     they
    -1.93
     for
    -1.91
     of
    -1.65
    %).
    -1.62
     їх
    -1.48
    㐂
    -1.45
     on
    -1.41
    fotografía
    -1.40
    Тарих
    -1.38
    ilustración
    -1.34
    POSITIVE LOGITS
    ”،
    1.66
    textrm
    1.39
    ateľ
    1.38
     хорошо
    1.35
    rovnik
    1.33
    стройка
    1.32
     nuevamente
    1.27
    ongyang
    1.27
     одной
    1.26
     ήταν
    1.26
    Activations Density 0.003%

    No Known Activations