© 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. 837
    Prev
    Next
    INDEX
    Explanations

    The neuron is tracking how far you are into the document—it fires in proportion to the token’s absolute position.

    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
     लेके
    0.58
    ського
    0.57
    лся
    0.55
    до
    0.54
    ⍵
    0.54
    itemconfig
    0.53
    ний
    0.51
    '=>'','
    0.50
     લઇ
    0.49
     потім
    0.49
    POSITIVE LOGITS
    ↵↵
    1.41
    ↵↵↵
    1.30
    ↵↵↵↵
    1.28
     Furthermore
    1.27
     Moreover
    1.22
    ↵↵↵↵↵
    1.17
     Additionally
    1.17
     Ultimately
    1.09
     Incidentally
    1.07
     Indeed
    1.05
    Activations Density 1.890%

    No Known Activations