© 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. 877
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on multi‐word business directory category labels (e.g. “Mining Equipment & Supplies,” “Real Estate Agents,” “Computer & Software Products,” 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
    0.41
     almost
    0.41
    }.")
    0.38
    总结
    0.38
     und
    0.36
    s
    0.36
     version
    0.35
     NULL
    0.35
    y
    0.34
    쨰
    0.34
    POSITIVE LOGITS
    ologija
    0.53
    その他
    0.49
     その他
    0.49
     Віль
    0.48
    ámara
    0.46
    鶚
    0.46
     شخصیت
    0.46
     personagem
    0.46
     دليل
    0.46
     personaggio
    0.46
    Activations Density 0.027%

    No Known Activations