© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 5710
    Prev
    Next
    INDEX
    Explanations

    two followed by a named item

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

    This neuron activates on references to Naruto anime fight videos (e.g. “Naruto vs. Gaara,” “9 Tails Chakra,” etc.).

    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
     ♦
    0.55
     mexico
    0.52
     Comment
    0.51
     ►
    0.51
     <>
    0.51
     cc
    0.50
     ·
    0.50
     <=>
    0.50
    agnetic
    0.49
    ന്തപു
    0.49
    POSITIVE LOGITS
    同学们
    0.68
    clickView
    0.64
    Read
    0.57
     दाख
    0.55
    すぐに
    0.55
    得到的
    0.55
    遇到的
    0.54
    面白
    0.54
     noch
    0.53
    还没有
    0.53
    Activations Density 0.022%

    No Known Activations