© 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. 9436
    Prev
    Next
    INDEX
    Explanations

    This neuron responds strongly to uncommon, low‐frequency tokens (i.e. rare or unusual 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
     এছাড়াও
    0.96
     मांझी
    0.84
    ativen
    0.80
    𝗼
    0.80
     რომელიც
    0.78
     बेटी
    0.75
    ératures
    0.75
     ના
    0.75
    𝐨
    0.75
     बच्ची
    0.74
    POSITIVE LOGITS
    v
    0.89
     Cylinder
    0.79
    et
    0.78
     odl
    0.77
    ch
    0.73
     Sparta
    0.73
    それは
    0.72
     innovators
    0.71
     cylinder
    0.70
     rappers
    0.70
    Activations Density 0.000%

    No Known Activations