© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 270
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively activates on abstract thematic nouns that name concepts, states, or events rather than on concrete objects or people.

    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
     등의
    0.40
    =
    0.37
    などの
    0.37
     Aspects
    0.35
    の
    0.33
     これらの
    0.33
     hoặc
    0.32
    的
    0.32
     Problems
    0.32
     Với
    0.32
    POSITIVE LOGITS
     togetherness
    0.57
     desperation
    0.56
     yester
    0.56
     grandeur
    0.55
     individualism
    0.55
     modernity
    0.55
     idealism
    0.54
     hypocrisy
    0.53
     defiance
    0.53
     nationalism
    0.52
    Activations Density 0.805%

    No Known Activations