© 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. 24-GEMMASCOPE-2-RES-16K
    7. 13174
    Prev
    Next
    INDEX
    Explanations

    downloading libraries/datasets

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

    This neuron detects words that signal seeking or presenting content—e.g. verbs like “looking,” “find,” “reading” or topic-introducing words like “about” and “concerning.”

    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_24_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
    וו
    0.80
    CPC
    0.71
    דינה
    0.70
    TNF
    0.70
    ƾ
    0.70
    Weyl
    0.68
    Republican
    0.67
    America
    0.66
     Вен
    0.66
    MCC
    0.65
    POSITIVE LOGITS
     ayaa
    0.79
     boutons
    0.78
     ampliamente
    0.72
     👉
    0.70
     pions
    0.70
     aastal
    0.69
     प्रतिसाद
    0.69
     embodiments
    0.67
     subito
    0.67
     ett
    0.66
    Activations Density 0.001%

    No Known Activations