© 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. 23928
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions and equations

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

    The neuron strongly activates on numeric tokens (numbers and numeric values) 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
    0
    -2.47
    ྅
    -2.13
    -
    -2.13
    3
    -1.99
    Keterangan
    -1.92
     colgante
    -1.84
    Sebagai
    -1.84
     estekak
    -1.82
     возможность
    -1.80
     мне
    -1.80
    POSITIVE LOGITS
     what
    2.34
     this
    2.27
     these
    2.17
     our
    1.94
    ロ
    1.90
     both
    1.86
    迓
    1.80
    可以使用
    1.77
    TagHelpers
    1.72
    ſelves
    1.72
    Activations Density 0.003%

    No Known Activations