© 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. 11307
    Prev
    Next
    INDEX
    Explanations

    Sabbath days and observances

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

    The neuron activates strongly on occurrences of “Sabbath” (and its variants like “sabbath,” “sab-bats,” etc.), i.e. references to the Sabbath observance.

    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
     verlie
    -2.17
     exemplos
    -2.14
     hintergrund
    -2.11
     anún
    -2.09
     fahrrad
    -2.03
     desafios
    -2.02
    色が
    -1.94
     diverses
    -1.91
    </strong>
    -1.91
    
    -1.90
    POSITIVE LOGITS
    All
    2.56
    If
    2.41
    We
    2.33
    This
    2.11
    全都
    2.03
    *}[
    2.02
    },
    1.99
    These
    1.91
    ８
    1.91
    On
    1.90
    Activations Density 0.002%

    No Known Activations