© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91393
    Prev
    Next
    INDEX
    Explanations

    coding and technical terms

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

    The neuron is detecting numeric tokens (i.e. strings of digits or numbers) especially in structured data like XML or code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    boton
    -0.81
    東日本
    -0.71
    Class
    -0.71
     ketchup
    -0.70
    Lap
    -0.70
     Lettre
    -0.69
     klaus
    -0.68
     templ
    -0.68
    TLS
    -0.68
    Visible
    -0.68
    POSITIVE LOGITS
     coding
    1.14
     código
    1.00
     Coding
    0.95
    LinkId
    0.88
    coding
    0.86
     strona
    0.85
     code
    0.84
     znak
    0.83
     площадь
    0.82
    ジナル
    0.81
    Activations Density 0.005%

    No Known Activations