© 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. 70419
    Prev
    Next
    INDEX
    Explanations

    words starting with Sn

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

    The neuron responds to the two‐letter sequence “Sn” (capital S, lowercase n) wherever it appears.

    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
    焄
    -3.44
    呖
    -3.03
    铙
    -2.81
    慜
    -2.75
    很
    -2.64
    鏨
    -2.64
    ?”
    -2.59
     inundated
    -2.56
    谖
    -2.48
    镞
    -2.47
    POSITIVE LOGITS
    ",
    2.92
    輒
    2.64
    ?
    2.59
    O
    2.41
     drie
    2.31
    嵎
    2.28
    いれば
    2.22
     foremost
    2.20
     quinze
    2.19
    \
    2.17
    Activations Density 0.007%

    No Known Activations