© 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. 26701
    Prev
    Next
    INDEX
    Explanations

    international characters and code

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

    The neuron fires on numeric tokens (strings of digits) anywhere 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
     that
    -1.07
    ANCIA
    -1.04
    = 
    -0.98
    =“
    -0.94
     étudiants
    -0.91
     versão
    -0.91
    (‘
    -0.91
    两者
    -0.90
    brtc
    -0.88
     zilver
    -0.87
    POSITIVE LOGITS
     אַ
    0.99
    問題
    0.96
     Consistency
    0.91
     Exploit
    0.90
    Terima
    0.87
    Sudah
    0.85
     juzgar
    0.85
    гать
    0.84
    喜爱
    0.84
    嬉しいです
    0.83
    Activations Density 0.000%

    No Known Activations