© 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. 74593
    Prev
    Next
    INDEX
    Explanations

    position behind

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

    The neuron activates on the preposition “behind.”

    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
    *
    -4.28
    )
    -3.97
    “
    -3.59
    /
    -3.44
     et
    -3.05
    '
    -3.02
    IN
    -2.94
    ↵↵
    -2.94
    [
    -2.83
    N
    -2.77
    POSITIVE LOGITS
    擽
    3.09
    
    3.09
    
    3.05
    
    3.02
    岨
    3.02
    滏
    2.98
    㐂
    2.98
    埽
    2.97
    葎
    2.91
     ſame
    2.84
    Activations Density 0.007%

    No Known Activations