© 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. 73441
    Prev
    Next
    INDEX
    Explanations

    mathematical and code variables

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

    The neuron is detecting standalone numeric tokens (numbers).

    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
    ريع
    -0.94
     hulle
    -0.85
     informace
    -0.82
    atase
    -0.81
     ongles
    -0.80
     беше
    -0.80
     perlas
    -0.79
     existant
    -0.79
    厂家
    -0.77
    曲は
    -0.77
    POSITIVE LOGITS
     eenvou
    0.90
     sıcak
    0.83
    >):
    0.82
     belangrijke
    0.82
    Retrouvez
    0.80
     wijze
    0.80
    )}}{
    0.78
     belangrijk
    0.78
     chamado
    0.77
    >())
    0.77
    Activations Density 0.004%

    No Known Activations