© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 13774
    Prev
    Next
    INDEX
    Explanations

    The neuron responds strongly to out‐of‐vocabulary or “special” tokens such as standalone numbers, uppercase acronyms, and possessive ’s markers.

    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
    ">
    0.75
    次の
    0.74
    ੀ
    0.73
    ी
    0.68
     forecast
    0.66
     fc
    0.66
     berikutnya
    0.66
     Autres
    0.66
     Wil
    0.65
     Theme
    0.65
    POSITIVE LOGITS
    motivated
    0.70
     Karite
    0.69
    istent
    0.69
    Ὅ
    0.68
    virt
    0.68
    withstanding
    0.65
    infused
    0.65
    assisted
    0.64
     деньги
    0.64
    стная
    0.64
    Activations Density 0.000%

    No Known Activations