© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8370
    Prev
    Next
    INDEX
    Explanations

    engagement, likes, supporters

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

    The neuron activates on numeric tokens—digits, dates, times, and other number strings in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     |
    0.70
    Manifest
    0.66
    Palindrome
    0.65
    Algorithm
    0.64
    Config
    0.63
     >
    0.62
    Page
    0.62
    Initialize
    0.59
     إِل
    0.59
    ×
    0.59
    POSITIVE LOGITS
     likes
    0.92
    likes
    0.86
     admirers
    0.85
     liking
    0.76
     Likes
    0.74
     dislikes
    0.72
     adherents
    0.71
     liked
    0.70
     persones
    0.70
     supporters
    0.69
    Activations Density 0.038%

    No Known Activations