© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12079
    Prev
    Next
    INDEX
    Explanations

    , and

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

    The neuron fires strongly on words that name share-targets or platforms (e.g. “family,” “Google Plus,” “Pinterest”) – in other words, it flags social-sharing context.

    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
    /
    0.64
    <?
    0.63
      
    0.62
    -​
    0.62
    Auth
    0.61
    And
    0.61
    Plus
    0.61
    而不
    0.61
    Enroll
    0.61
    POSITIVE LOGITS
     &,
    0.89
     ও
    0.87
     &/
    0.83
     மற்றும்
    0.82
     &
    0.81
     compds
    0.80
     ಮತ್ತು
    0.74
     prepd
    0.73
     &(
    0.71
     ಹಾಗೂ
    0.71
    Activations Density 0.168%

    No Known Activations