© 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. 10-GEMMASCOPE-RES-131K
    7. 42445
    Prev
    Next
    INDEX
    Explanations

    note or letter

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

    The neuron fires strongly on words referring to written messages—especially “note” or “letter.”

    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
    it
    -1.44
    .
    -1.38
    laient
    -1.38
     insistent
    -1.30
    2
    -1.30
     الوزراء
    -1.28
              
    -1.27
    while
    -1.26
               
    -1.26
                
    -1.23
    POSITIVE LOGITS
    なんです
    1.46
     bahwa
    1.45
     that
    1.35
    jangkau
    1.33
     vroeg
    1.29
    gemeester
    1.28
     Desenvolvimento
    1.27
     lema
    1.27
    áklad
    1.26
    ߰
    1.26
    Activations Density 0.041%

    No Known Activations