© 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. 22-GEMMASCOPE-RES-131K
    7. 70355
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions

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

    The neuron is detecting numeric tokens (standalone numbers) 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_22/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
    prit
    -1.09
     múltiple
    -1.08
    おわりに
    -1.00
     Για
    -0.98
    himo
    -0.96
    vii
    -0.93
    unless
    -0.91
    ylen
    -0.91
     Phạm
    -0.90
     and
    -0.89
    POSITIVE LOGITS
    そうです
    1.10
    憩
    1.05
    owanie
    1.02
     повин
    0.94
     []
    0.94
     __
    0.93
    そうですが
    0.93
    <bos>
    0.93
    áticas
    0.92
     '*':
    0.91
    Activations Density 0.094%

    No Known Activations