© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5460
    Prev
    Next
    INDEX
    Explanations

    anti- sentiment

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

    This neuron activates on occurrences of the bound morpheme “anti-” (as in anti-Romani, anti-Brexit, anti-government, etc.), flagging compound adjectives that start with “anti-.”

    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_24_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
    র
    0.82
    ेशन
    0.79
    اية
    0.77
    ز
    0.76
    ০০
    0.75
     Indicator
    0.75
     Database
    0.70
    ﻯ
    0.70
    0
    0.70
    하는
    0.69
    POSITIVE LOGITS
     dignitaries
    0.63
     suceder
    0.63
    ⁈
    0.61
     towns
    0.60
    CLUS
    0.60
     worshippers
    0.60
     griev
    0.59
     ہوئی
    0.58
     luxuries
    0.57
    inationals
    0.56
    Activations Density 0.004%

    No Known Activations