© 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. 6872
    Prev
    Next
    INDEX
    Explanations

    non-special or alternative kinds

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

    The neuron is triggered by hyphenated prefixes or compounds (e.g. the “non-” in “non-small-cell”).

    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
     primar
    -1.09
     parter
    -0.95
     Zang
    -0.95
    抬起头
    -0.91
     любых
    -0.91
     ولو
    -0.91
     スタンダード
    -0.91
     основной
    -0.91
     primaria
    -0.89
     réguli
    -0.89
    POSITIVE LOGITS
     specialty
    1.38
     special
    1.27
     alternative
    1.13
     tzw
    1.08
     hybrid
    1.06
     specialized
    1.05
    特殊
    1.05
     multi
    1.05
    特殊的
    0.97
     specjal
    0.96
    Activations Density 0.383%

    No Known Activations