© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3492
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on terms naming commercial offerings—like products, solutions, hardware, industries, services—i.e. words used in marketing or business feature descriptions.

    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
    ر
    0.98
     Computational
    0.98
    кту
    0.94
    ور
    0.92
    वी
    0.92
    hhhh
    0.91
     NX
    0.91
    ﻯ
    0.90
    ோ
    0.89
     مرح
    0.88
    POSITIVE LOGITS
     издели
    1.16
    IllegalArgument
    1.13
     kuten
    1.08
     изделия
    1.05
     изделий
    1.05
     chimique
    1.05
    ObjectUnderTest
    1.03
     άλλο
    1.03
     Produkten
    1.01
    制品
    1.00
    Activations Density 2.974%

    No Known Activations