© 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. 12865
    Prev
    Next
    INDEX
    Explanations

    The neuron is selectively responding to uncommon or low-frequency tokens (e.g. rare words and proper names).

    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
    z
    0.74
     Notably
    0.70
    Amanda
    0.70
     Excluding
    0.70
    zhang
    0.69
    espec
    0.66
     Amanda
    0.66
    chant
    0.65
    eeee
    0.63
     Confirm
    0.62
    POSITIVE LOGITS
    ﻱ
    0.91
    ektedir
    0.84
     понимают
    0.81
     zwią
    0.79
     Tanık
    0.79
     postoje
    0.78
    하시오
    0.77
    ﻢ
    0.77
     ませ
    0.77
    ResourceId
    0.77
    Activations Density 0.000%

    No Known Activations