© 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. 16210
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    The neuron spikes whenever it encounters an unusually rare or out‐of‐vocabulary token 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
    iem
    0.68
    ipe
    0.63
    d
    0.63
    nent
    0.62
    i
    0.62
    ім
    0.61
    tiin
    0.61
     weaken
    0.61
    ]");
    0.59
    t
    0.58
    POSITIVE LOGITS
     nelle
    0.97
     designado
    0.91
     município
    0.90
     consiglio
    0.89
     cinéma
    0.89
     bangunan
    0.88
     établissements
    0.88
     municípios
    0.86
     começou
    0.85
     recinto
    0.85
    Activations Density 0.000%

    No Known Activations