© 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. 5037
    Prev
    Next
    INDEX
    Explanations

    export class Component

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

    The neuron is effectively dead—it never activates on any token.

    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
    梩
    0.97
    itipi
    0.75
    óricos
    0.73
     topologically
    0.71
    straction
    0.70
    transitions
    0.70
    類型
    0.70
    समाज
    0.70
    \%),
    0.70
     剤
    0.70
    POSITIVE LOGITS
     ER
    0.85
     n
    0.82
     f
    0.80
    arin
    0.77
     Octopus
    0.77
     ES
    0.77
     AB
    0.75
     PC
    0.75
     An
    0.74
     IM
    0.73
    Activations Density 0.005%

    No Known Activations