© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 9580
    Prev
    Next
    INDEX
    Explanations

    This neuron selectively fires on long, content-bearing nouns (especially multisyllabic “topic” nouns such as “scenario,” “Locations,” “accommodation,” etc.).

    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
    ل
    0.84
    ரி
    0.82
    ল
    0.82
    मधील
    0.80
    ম
    0.80
    ڈن
    0.78
    מ
    0.78
    у
    0.77
    на
    0.77
    GEBURTS
    0.77
    POSITIVE LOGITS
    oves
    0.86
    iger
    0.82
     Tiene
    0.80
     tienes
    0.77
    ichel
    0.75
     terceros
    0.73
    ibly
    0.72
    ice
    0.70
     pantalla
    0.70
     cell
    0.69
    Activations Density 0.000%

    No Known Activations