© 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. 13368
    Prev
    Next
    INDEX
    Explanations

    come on

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

    The neuron activates specifically on the verb “come” (and its past‐tense “came”).

    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
    Curve
    0.71
    status
    0.61
    eles
    0.59
    curve
    0.57
    lees
    0.55
     অবসর
    0.55
    消
    0.55
    CV
    0.54
    的高度
    0.53
    ✗
    0.53
    POSITIVE LOGITS
     apology
    0.63
     Udaipur
    0.60
    گاه
    0.57
     نق
    0.57
    となって
    0.57
     compartilhar
    0.56
     Forth
    0.56
     JAN
    0.56
     escalator
    0.56
     Jind
    0.55
    Activations Density 0.006%

    No Known Activations