© 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. 10-GEMMASCOPE-RES-131K
    4. 74942
    Prev
    Next
    INDEX
    Explanations

    AM

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

    The neuron activates on tokens containing the substring “AM,” chiefly marking acronyms for cell adhesion molecules (e.g. ICAM-1, VCAM-1).

    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
     dünya
    -1.48
     
    -1.32
     ziyaretçi
    -1.30
     Have
    -1.30
     Now
    -1.29
     And
    -1.28
     would
    -1.28
     remitted
    -1.27
     arşiv
    -1.26
     HAVE
    -1.24
    POSITIVE LOGITS
    
    1.58
     actuelles
    1.41
     sposob
    1.38
    ኧ
    1.37
    AM
    1.35
     commerciales
    1.32
     you
    1.31
     είναι
    1.30
     подарок
    1.28
    нении
    1.27
    Activations Density 0.016%

    No Known Activations