© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7534
    Prev
    Next
    INDEX
    Explanations

    Tuesday

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is not looking for any particular semantic feature of the words themselves but rather where they occur in the text—it steadily increases activation for tokens that appear later (deeper) in the document.

    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
    od
    0.97
    ou
    0.94
    er
    0.90
    ín
    0.86
    ow
    0.84
    op
    0.83
    ות
    0.80
    oder
    0.77
     chữa
    0.75
    aan
    0.75
    POSITIVE LOGITS
    蛍光
    0.98
    Dropbox
    0.89
    дне
    0.83
    бычно
    0.79
    MyToolkit
    0.79
    朓
    0.78
    ❒
    0.77
    宻
    0.77
    โรงแรม
    0.76
    eyeglasses
    0.76
    Activations Density 0.000%

    No Known Activations