© 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. 113491
    Prev
    Next
    INDEX
    Explanations

    causal relationships and subsequent states

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

    The neuron strongly activates on the preposition “in,” especially when it begins common technical phrases like “in turn,” “in its early stages,” or “in some cases.”

    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
     rempliss
    -1.65
     нѣ
    -1.58
    lenül
    -1.48
    kurtka
    -1.48
     niečo
    -1.48
     всѣ
    -1.47
     huiles
    -1.47
    ₰
    -1.46
    魉
    -1.46
     tewas
    -1.44
    POSITIVE LOGITS
    ing
    1.84
       
    1.64
      
    1.62
     my
    1.47
    s
    1.46
            
    1.40
         
    1.37
    Ｑ
    1.36
    a
    1.35
     me
    1.32
    Activations Density 0.016%

    No Known Activations