© 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. 93376
    Prev
    Next
    INDEX
    Explanations

    citations and technical details

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

    The neuron is specialized for detecting numeric tokens (e.g. years, volume/page numbers, and other digits) 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
    TypedDataSet
    -0.97
    新华
    -0.94
     cuộc
    -0.93
    顕
    -0.93
    это
    -0.91
     đảo
    -0.91
    राज
    -0.90
    gantung
    -0.89
    очень
    -0.87
     establecidos
    -0.87
    POSITIVE LOGITS
    สำคัญ
    0.92
    気持ち
    0.91
    話は
    0.90
     Ignatius
    0.90
     Nome
    0.87
    uscita
    0.87
    気持ちが
    0.85
     lít
    0.84
    運び
    0.83
     хочется
    0.82
    Activations Density 0.001%

    No Known Activations