© 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. 6148
    Prev
    Next
    INDEX
    Explanations

    dialog width

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

    This neuron activates on UI/navigation or dialog‐box markers (e.g. “dialog,” “content,” “Close,” “Page,” “Message”).

    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
    否
    0.60
    Butter
    0.55
    อฟ
    0.54
    当量
    0.53
    Ain
    0.52
    足
    0.52
    butter
    0.52
    देवा
    0.50
    ناک
    0.50
    obacter
    0.50
    POSITIVE LOGITS
    ड्ड
    0.60
     messageShow
    0.59
     professores
    0.58
     करीब
    0.57
     Trouvez
    0.57
     होमवर्क
    0.56
    蒿
    0.56
    лата
    0.55
     brings
    0.54
     Kelas
    0.53
    Activations Density 0.000%

    No Known Activations