© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101187
    Prev
    Next
    INDEX
    Explanations

    ABC media, news, and transporters

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

    The neuron strongly activates on occurrences of the substring “ABC,” whether as part of the phrase “ATP-Binding Cassette (ABC)” or the standalone acronym “ABC.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    なども
    -2.39
     reconoc
    -2.38
     standout
    -2.27
    瑨
    -2.22
     
    -2.22
     […]
    -2.19
     parecen
    -2.11
    たちの
    -2.11
    仿佛
    -2.09
     llegan
    -2.08
    POSITIVE LOGITS
    酲
    2.70
    鯓
    2.59
    媖
    2.58
    𓋼
    2.55
    戽
    2.52
    榈
    2.50
    
    2.45
    ຼ
    2.45
    tamos
    2.45
    }$
    2.41
    Activations Density 0.009%

    No Known Activations