© 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. 902
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on unusually rare or low‐frequency tokens (i.e. “increasing,” “medians,” “Panel,” “starting,” 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
    摞
    0.75
    iser
    0.72
    षद
    0.72
     siente
    0.71
     Recordemos
    0.71
     Peut
    0.70
     Reinhardt
    0.70
    ে
    0.70
     calendario
    0.69
     saque
    0.68
    POSITIVE LOGITS
    這一
    0.80
    對
    0.77
    極
    0.77
    ある
    0.74
    首先
    0.74
    kx
    0.71
    ﻼ
    0.71
     dây
    0.71
     tämän
    0.70
    众人
    0.69
    Activations Density 0.017%

    No Known Activations