© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6038
    Prev
    Next
    INDEX
    Explanations

    crisis resources

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

    The neuron is triggered by non‐lexical “noise” tokens—things like hashtags, inline code or CSS snippets, special symbols, file names, and other formatting/markup artifacts.

    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_24_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
     biotechnology
    0.76
     fibers
    0.69
     neighboring
    0.67
     aquaculture
    0.66
    नात्मक
    0.63
     biotechn
    0.63
    dbi
    0.62
    筤
    0.62
     cyclospor
    0.61
     fibres
    0.61
    POSITIVE LOGITS
     retweet
    0.98
    tweet
    0.93
     tweet
    0.92
     Tweet
    0.90
     अपलोड
    0.88
     HTTP
    0.85
    Screenshot
    0.83
     Snapchat
    0.82
     screenshot
    0.82
    imgur
    0.82
    Activations Density 1.484%

    No Known Activations