© 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. 11461
    Prev
    Next
    INDEX
    Explanations

    action completion or continuation

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires strongly on finite verbs (both past‐tense “–ed” forms and present‐tense third-person forms).

    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
     когда
    1.52
     quando
    1.42
     when
    1.40
    when
    1.34
     cuando
    1.34
     когато
    1.33
    當
    1.30
     जब
    1.26
    quando
    1.26
    当
    1.24
    POSITIVE LOGITS
     overseas
    0.53
     ulang
    0.51
     remarquer
    0.51
    랗
    0.50
     Ch
    0.49
     mid
    0.49
     Center
    0.49
    ুপ
    0.48
     ponownie
    0.48
     очередной
    0.48
    Activations Density 0.209%

    No Known Activations