© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 2047
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by technical specification and feature terms (e.g. “accuracy,” “machines,” “tables,” “servers,” “coating,” etc.) in product‐or engineering‐style 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
     There
    0.65
     ঃ
    0.64
     Although
    0.56
     Normally
    0.52
     .$
    0.52
     由于
    0.52
     Also
    0.52
     Each
    0.52
     通常
    0.52
    0
    0.52
    POSITIVE LOGITS
     geopolitical
    0.52
     societal
    0.51
     gesellschaft
    0.50
     reimag
    0.49
     azok
    0.47
     terroir
    0.46
     geopol
    0.45
     détente
    0.45
     analytics
    0.43
     soziale
    0.43
    Activations Density 0.000%

    No Known Activations