© 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. 15501
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on semantically important content words (e.g. key nouns or 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
     Kult
    0.84
     strategie
    0.82
     Cliente
    0.82
     Strategies
    0.79
     Muda
    0.79
     rooted
    0.77
    ,
    0.77
     partage
    0.75
     stratégies
    0.75
     as
    0.74
    POSITIVE LOGITS
     করোনাভাই
    0.95
     இந்த
    0.89
    இந்த
    0.89
    በ
    0.88
    ୮
    0.84
     તથા
    0.82
     बजकर
    0.80
    ៨
    0.79
    {$\
    0.78
    <h5>
    0.78
    Activations Density 0.000%

    No Known Activations