© 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. 4124
    Prev
    Next
    INDEX
    Explanations

    The neuron is tuned to pick out relatively long, uncommon multisyllabic content words.

    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
    Você
    1.05
    ®.
    0.96
    ។
    0.94
    Então
    0.93
    ™.
    0.91
    Assassin
    0.85
    ​.
    0.84
    €.
    0.84
    .​​
    0.84
    Parrocchia
    0.83
    POSITIVE LOGITS
     hitherto
    1.00
     physico
    0.94
     of
    0.91
     formulae
    0.91
     researches
    0.89
     radiations
    0.88
     utterances
    0.88
     epochs
    0.88
     morphisms
    0.87
     evidences
    0.87
    Activations Density 0.001%

    No Known Activations