© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65817
    Prev
    Next
    INDEX
    Explanations

    sheets and layers

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

    This neuron detects technical numeric tokens in material‐science contexts—especially numbers and subscripts in chemical formulas and dimensional descriptors.

    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
    tikum
    -0.74
    Pherson
    -0.71
    lnie
    -0.71
     смета
    -0.71
     Duffy
    -0.69
     Tempe
    -0.68
     mentorship
    -0.68
    Aya
    -0.68
     Tampere
    -0.68
     vorder
    -0.67
    POSITIVE LOGITS
     sheets
    1.48
     exfoli
    1.38
     layers
    1.34
     layered
    1.29
     stacks
    1.27
     sheet
    1.16
     stacked
    1.16
     layering
    1.16
     foli
    1.12
     flakes
    1.12
    Activations Density 0.106%

    No Known Activations