© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9654
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on isolated whole-word tokens (i.e. words that the tokenizer leaves unsplit), especially those of moderate rarity.

    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
    ొ
    0.91
     ਦਿ
    0.90
    𝘇
    0.85
    nz
    0.84
    ب
    0.83
    kl
    0.82
    lä
    0.82
    ke
    0.82
    에
    0.82
    g
    0.78
    POSITIVE LOGITS
     Contact
    0.85
     Hiking
    0.80
     Adapted
    0.77
     época
    0.77
     Networking
    0.71
     Output
    0.71
     οπο
    0.70
     mâles
    0.70
     BoxLayout
    0.70
     Energia
    0.70
    Activations Density 0.000%

    No Known Activations