© 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. 33710
    Prev
    Next
    INDEX
    Explanations

    start of phrases

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

    This neuron is effectively inactive—it does not detect or respond to any specific token pattern.

    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
    ☺☺
    -1.27
     onsdag
    -1.27
     дола
    -1.23
     Frankrijk
    -1.23
     margiela
    -1.21
    ことから
    -1.20
    ugos
    -1.20
    不堪
    -1.20
    ««
    -1.19
     fredag
    -1.18
    POSITIVE LOGITS
     gesamten
    1.55
    完成です
    1.45
     eigentlichen
    1.45
     oberen
    1.41
     и
    1.38
     และ
    1.37
     gäng
    1.34
     [
    1.34
     same
    1.32
    readFileSync
    1.32
    Activations Density 0.012%

    No Known Activations