© 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. 5950
    Prev
    Next
    INDEX
    Explanations

    `public` keyword

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

    This neuron responds to tokens containing the character sequence “Mor.”

    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
    érience
    0.55
     golongan
    0.54
     BFS
    0.51
    涮
    0.51
     گرو
    0.50
     entanglement
    0.50
     výkon
    0.50
    itee
    0.50
    🧡
    0.50
     anga
    0.49
    POSITIVE LOGITS
    ILabel
    0.54
    ас
    0.51
     አለ
    0.51
    Academy
    0.50
    Meter
    0.47
    ወስ
    0.47
    ıda
    0.46
    ጨማሪ
    0.46
    Acceleration
    0.46
     academies
    0.46
    Activations Density 0.002%

    No Known Activations