© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113551
    Prev
    Next
    INDEX
    Explanations

    begins with a

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

    The neuron detects phrasing that introduces the start of an event or sequence (e.g. “began with,” “kicked off with,” “commences with,” “got going with”).

    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
    iram
    -1.66
        
    -1.63
     prossimo
    -1.48
     was
    -1.45
                  
    -1.41
                
    -1.41
               
    -1.40
     recently
    -1.39
     bellissimo
    -1.38
    ∎
    -1.37
    POSITIVE LOGITS
     parfü
    1.80
    瑧
    1.79
     parfüm
    1.76
     godk
    1.73
    一張
    1.69
     continúas
    1.66
     pü
    1.65
    Плюсы
    1.62
    🏢
    1.59
    焢
    1.53
    Activations Density 0.044%

    No Known Activations