© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 643
    Prev
    Next
    INDEX
    Explanations

    variable contains"}

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

    This neuron activates on concrete object or component nouns referring to physical parts or equipment.

    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
    。《
    0.68
    。
    0.68
    人了
    0.67
    ！！
    0.66
    ！！！
    0.66
    ！？
    0.66
    ？！
    0.66
    。“
    0.66
     защото
    0.66
    ؟!
    0.64
    POSITIVE LOGITS
     undergoes
    2.03
     receives
    1.84
     contains
    1.76
     possesses
    1.75
     behaves
    1.72
     possède
    1.61
     occupies
    1.55
     retains
    1.55
     has
    1.53
     becomes
    1.52
    Activations Density 0.927%

    No Known Activations