© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15592
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on multi-letter uppercase abbreviations or acronyms (e.g. SSL, SSIS).

    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
     andRow
    0.93
    andfeel
    0.91
    createInfo
    0.90
    examtype
    0.87
    妓
    0.86
    ジュン
    0.84
    🍵
    0.83
    咲
    0.82
    Apakah
    0.82
    ጎ
    0.82
    POSITIVE LOGITS
     D
    0.80
     E
    0.79
     C
    0.79
     S
    0.78
     B
    0.78
     various
    0.78
     T
    0.77
     F
    0.76
     Air
    0.76
     M
    0.75
    Activations Density 14.264%

    No Known Activations