© 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. 7859
    Prev
    Next
    INDEX
    Explanations

    software updates and solutions

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

    The neuron fires on boilerplate and administrative metadata tokens—things like section‐heading labels (“Tip,” “Contact”), disclaimers (“©,” “maximum extent permitted”), and other navigational/structural markers.

    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
    หลัง
    0.83
    อ
    0.82
     উদ্দেশ্য
    0.81
    ﻲ
    0.80
    0.79
     morte
    0.74
     vontade
    0.73
     продолжи
    0.73
     главный
    0.72
     Exter
    0.72
    POSITIVE LOGITS
    t
    0.86
    capabilities
    0.85
    tracing
    0.79
     radiating
    0.76
    errors
    0.73
     sprouting
    0.72
    regation
    0.72
    //
    0.71
    traces
    0.70
     archiving
    0.70
    Activations Density 0.004%

    No Known Activations