© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2394
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric tokens (i.e. numbers or tokens containing digits).

    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
    atthena
    0.74
    ateboard
    0.70
    aparikkh
    0.69
    ẖ
    0.68
    avacan
    0.68
    atthakath
    0.67
    icycl
    0.66
    uckoo
    0.66
    avacanam
    0.65
    nicheskij
    0.65
    POSITIVE LOGITS
    ",
    0.61
    ";
    0.53
     not
    0.52
    <unused60>
    0.51
    不仅
    0.51
     altres
    0.48
    <unused63>
    0.48
     ",
    0.47
     en
    0.47
     중에
    0.46
    Activations Density 0.113%

    No Known Activations