© 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. 10041
    Prev
    Next
    INDEX
    Explanations

    The neuron flags unusually rare or low-frequency tokens—i.e. it detects out-of-vocabulary or infrequent 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
     дана
    0.89
    ляются
    0.86
    䬲
    0.83
     Neuer
    0.83
    ynthetic
    0.82
    iatric
    0.81
    ленное
    0.81
    ována
    0.81
    windigkeit
    0.80
    دوس
    0.80
    POSITIVE LOGITS
     myocytes
    0.73
     tying
    0.66
     racks
    0.63
     kịp
    0.60
     パ
    0.59
     weakening
    0.59
     href
    0.58
    િયા
    0.58
     Tark
    0.58
     undermining
    0.57
    Activations Density 0.000%

    No Known Activations