© 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. 118191
    Prev
    Next
    INDEX
    Explanations

    SM initialisms and acronyms

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

    The neuron strongly activates on uppercase “SM” substrings (often as part of acronyms like SMU, SMC, SMN, etc.).

    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
    attu
    -0.74
     moistur
    -0.73
    ང་
    -0.73
     població
    -0.72
     loads
    -0.72
     înd
    -0.72
     menerima
    -0.69
    mão
    -0.69
    ällor
    -0.69
     nothing
    -0.68
    POSITIVE LOGITS
     SM
    1.97
    SM
    1.58
     sm
    1.55
     Sm
    1.43
     SMC
    1.27
    sm
    1.25
     SMT
    1.22
    SMT
    1.21
     SMA
    1.21
    سم
    1.21
    Activations Density 0.082%

    No Known Activations