© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1527
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly sensitive to numeric tokens (e.g. IDs, version numbers, measurements, and other numerical constants).

    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_31_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
    ($"{
    0.64
    ("
    0.58
    <>();
    0.58
     sợ
    0.58
    בי
    0.57
     inorder
    0.57
     $_
    0.57
    <0x0D>
    0.56
    Trusted
    0.55
     niet
    0.55
    POSITIVE LOGITS
    inkel
    0.71
    ähne
    0.70
     Recordings
    0.70
     Recreation
    0.68
     Metabolism
    0.67
    ufu
    0.66
     Casualty
    0.66
    ído
    0.65
     جائزے
    0.64
    వంటి
    0.64
    Activations Density 0.001%

    No Known Activations