© 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. 34-GEMMASCOPE-RES-131K
    7. 65782
    Prev
    Next
    INDEX
    Explanations

    SL followed by other letters

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

    The neuron fires when it sees the two-letter sequence “SL” (in upper or lower case) at the start of a token.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    érées
    -0.77
    Sudden
    -0.75
    тация
    -0.73
    erschrank
    -0.73
     unclean
    -0.71
    TokenNameCOMMA
    -0.70
    hages
    -0.70
    Seguro
    -0.70
    दै
    -0.69
     Lovers
    -0.68
    POSITIVE LOGITS
     sl
    1.73
     SL
    1.61
    SL
    1.41
     Sl
    1.32
    sl
    1.25
     슬
    1.20
    Sl
    1.20
     SLC
    1.14
     slurry
    1.11
     sla
    1.09
    Activations Density 0.044%

    No Known Activations