© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13658
    Prev
    Next
    INDEX
    Explanations

    appropriate and proper

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

    This neuron detects words that express correctness or suitability, such as “proper,” “appropriate,” or “suitable.”

    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
    が良い
    0.72
    事実
    0.68
    原来的
    0.63
    がいい
    0.62
    が好き
    0.61
    埤
    0.61
    原本
    0.61
    便于
    0.60
     принципе
    0.60
     possibilidades
    0.59
    POSITIVE LOGITS
     functioning
    0.90
     properly
    0.88
    proper
    0.87
    Proper
    0.86
    functioning
    0.84
     Proper
    0.84
     proper
    0.80
     sized
    0.78
     Properly
    0.76
    sized
    0.75
    Activations Density 0.214%

    No Known Activations