© 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. 6248
    Prev
    Next
    INDEX
    Explanations

    The neuron is essentially flagging unusually rare or low‐frequency tokens in the text.

    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
    ंच
    0.75
    িতাম
    0.75
    Gestion
    0.74
     collegamento
    0.70
    ؤ
    0.69
    黉
    0.68
    їв
    0.67
    حمد
    0.67
    なども
    0.67
    ҽ
    0.67
    POSITIVE LOGITS
     Гру
    0.80
     inFile
    0.78
     cH
    0.76
     Ngf
    0.73
     JSONArray
    0.73
    cH
    0.70
     currentCol
    0.70
     вопро
    0.69
    樖
    0.68
    ↵
    0.68
    Activations Density 0.000%

    No Known Activations