© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81761
    Prev
    Next
    INDEX
    Explanations

    words ending in -ian or -ism

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

    The neuron detects tokens ending with the suffix “ian.”

    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
    amazing
    -0.93
    瘆
    -0.91
     飾り
    -0.91
     paulista
    -0.89
     cloche
    -0.89
    eon
    -0.88
     スイーツ
    -0.88
    鄚
    -0.86
     intelligente
    -0.85
    course
    -0.85
    POSITIVE LOGITS
    ism
    1.91
    ized
    1.31
    ISM
    1.02
    na
    1.02
    ize
    0.99
    ismo
    0.96
    isms
    0.94
    izing
    0.93
    isme
    0.92
    esimo
    0.91
    Activations Density 0.055%

    No Known Activations