© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33369
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with n

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

    The neuron activates on numeric tokens (digits, numbers and numeric constants) 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
    гром
    -0.98
    鍮
    -0.97
     życia
    -0.94
    Тарих
    -0.90
    gica
    -0.90
    立
    -0.88
     الحكومة
    -0.88
     הנו
    -0.85
     advirtió
    -0.85
    yczne
    -0.85
    POSITIVE LOGITS
    -/**
    0.90
     strengthen
    0.90
    termilk
    0.90
    僕が
    0.88
    рия
    0.87
    <td>
    0.87
    私が
    0.84
    以上就是
    0.84
     vilken
    0.84
    。。。
    0.83
    Activations Density 0.022%

    No Known Activations