© 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. 10-GEMMASCOPE-RES-131K
    7. 65206
    Prev
    Next
    INDEX
    Explanations

    type declarations

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

    The neuron primarily fires on standalone numeric literals (e.g. version numbers or other numeric constants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ְּ
    -2.52
    ּוֹ
    -2.41
    ַּ
    -2.41
    ֶּ
    -2.39
     their
    -2.19
    ִּ
    -2.14
    ֵּ
    -2.05
     two
    -2.05
    ָּ
    -1.82
     бампер
    -1.78
    POSITIVE LOGITS
     chré
    2.05
     tertinggi
    1.80
     блюдо
    1.79
     vanil
    1.78
     marta
    1.75
     云
    1.71
     akhirnya
    1.71
     miſ
    1.70
     Ayam
    1.66
     bahkan
    1.65
    Activations Density 0.230%

    No Known Activations