© 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. 3547
    Prev
    Next
    INDEX
    Explanations

    The neuron detects technical specification and parameter-related keywords in documentation.

    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
     magnitude
    0.72
     aes
    0.71
     distanced
    0.69
    }`)
    0.66
    ன்கள்
    0.66
     shores
    0.65
     тело
    0.65
    +}$
    0.65
    겐
    0.65
    0.64
    POSITIVE LOGITS
    ا
    0.88
    ombrie
    0.85
    Nina
    0.83
    arjo
    0.82
    RequestId
    0.82
     Adriana
    0.81
    柢
    0.80
     ภาษา
    0.79
     HUOBI
    0.77
     جناب
    0.77
    Activations Density 0.025%

    No Known Activations