© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9659
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on salient content words—especially longer, informational nouns and verbs—rather than on common function words.

    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
    س
    0.71
     Customs
    0.70
    দ্ব
    0.68
    Records
    0.66
     Municipality
    0.66
    ∇
    0.66
    ńskiej
    0.65
    아
    0.65
    Sys
    0.63
     Records
    0.63
    POSITIVE LOGITS
     bosques
    0.83
     Apesar
    0.82
    imsu
    0.82
    ENIDO
    0.82
    足以
    0.80
     criando
    0.80
     backlit
    0.79
    者を
    0.79
    纓
    0.79
    ても
    0.79
    Activations Density 0.000%

    No Known Activations