© 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. 1168
    Prev
    Next
    INDEX
    Explanations

    the followed by specific words

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

    The neuron consistently activates on numeric literal tokens (e.g. years, counts, codes) in code and comments.

    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
     konflikt
    -0.89
     kompakt
    -0.81
    optera
    -0.79
     kompati
    -0.78
     Vierge
    -0.77
    くま
    -0.76
     kompak
    -0.75
    斯拉
    -0.75
    υτό
    -0.74
     hablaba
    -0.74
    POSITIVE LOGITS
    >;<
    0.78
    階級
    0.77
     given
    0.75
    apar
    0.73
     Donner
    0.72
    燎
    0.72
     என்
    0.72
     migrations
    0.72
    Quoted
    0.72
     Yay
    0.71
    Activations Density 0.001%

    No Known Activations