© 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. 19890
    Prev
    Next
    INDEX
    Explanations

    9

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

    The neuron activates on standalone numeric tokens or short digit sequences (e.g. verse numbers, ISBN or phone‐number fragments).

    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
     Of
    -1.60
     The
    -1.59
     where
    -1.58
    佧
    -1.52
     which
    -1.52
     So
    -1.51
    </i>
    -1.46
     they
    -1.45
     аналоги
    -1.45
     Which
    -1.40
    POSITIVE LOGITS
    1
    1.78
    thansa
    1.69
    Gön
    1.63
     знали
    1.59
    '
    1.54
     bubbly
    1.53
    hasilkan
    1.52
    -
    1.49
    8
    1.41
     nutty
    1.38
    Activations Density 0.029%

    No Known Activations