© 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. 65299
    Prev
    Next
    INDEX
    Explanations

    language and code fragments

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

    The neuron fires on numeric literals (sequences of 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_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
    Dib
    -0.82
     potřeb
    -0.81
    冽
    -0.78
     gettin
    -0.77
    oxia
    -0.77
    Kitty
    -0.75
    刑
    -0.74
    応
    -0.74
     gedeelte
    -0.72
    tomcat
    -0.71
    POSITIVE LOGITS
     logos
    0.85
     LEVEL
    0.84
     denim
    0.84
    idyl
    0.83
    zaak
    0.82
     dati
    0.80
     язы
    0.79
     stains
    0.79
     libres
    0.78
     elegans
    0.78
    Activations Density 0.000%

    No Known Activations