© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66287
    Prev
    Next
    INDEX
    Explanations

    cationic compounds and processes

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

    chemical terms related to ionic compounds, particularly the word "cationic" and other ion-related terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects chemistry terms ending in the suffix “-ic,” especially ionic and cationic/anionic adjectives.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alderman
    -0.76
     deal
    -0.76
     IMP
    -0.72
    idler
    -0.71
    ohy
    -0.71
    ideo
    -0.71
    ɡ
    -0.70
     batman
    -0.68
    uelos
    -0.67
     anions
    -0.67
    POSITIVE LOGITS
     exchange
    0.89
    Exchange
    0.85
    exchange
    0.84
     Exchange
    0.76
     forme
    0.75
    雑誌
    0.74
    Sites
    0.71
    приятия
    0.70
    enya
    0.69
     ép
    0.68
    Activations Density 0.084%

    No Known Activations