© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12974
    Prev
    Next
    INDEX
    Explanations

    in light of

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

    The neuron detects occurrences of the phrase “in light of,” signaling that the text is introducing a contextual or explanatory clause.

    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
    </h1>
    -2.41
     was
    -2.09
    на
    -1.91
     divertida
    -1.91
    </h5>
    -1.85
     Both
    -1.78
     })
    
    -1.74
    %;
    
    -1.72
     Many
    -1.71
    >}
    -1.70
    POSITIVE LOGITS
     of
    1.80
    錞
    1.71
     eenig
    1.66
    鈈
    1.63
    
    1.60
     несколь
    1.57
     firsthand
    1.55
     :.
    1.55
     maestros
    1.55
    ²,
    1.55
    Activations Density 0.008%

    No Known Activations