© 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. 111125
    Prev
    Next
    INDEX
    Explanations

    ress endings

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

    The neuron activates on the character sequence “ress,” i.e. words containing the suffix “ress.”

    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
    न
    -3.02
    (
    -2.83
     fueled
    -2.78
     he
    -2.78
     Carefully
    -2.73
    [
    -2.61
    \
    -2.55
     
    -2.48
     Achieving
    -2.44
     одну
    -2.34
    POSITIVE LOGITS
    al
    2.98
     him
    2.78
     {
    2.64
    ଞ
    2.50
     совета
    2.45
    骘
    2.42
     białe
    2.38
    Pued
    2.36
     uwagi
    2.36
    咐
    2.31
    Activations Density 0.008%

    No Known Activations