© 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. 11326
    Prev
    Next
    INDEX
    Explanations

    extension or deformations

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

    This neuron is specifically triggered by the three‐word sequence “descends to an” in formal mathematical prose.

    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
    siehe
    -1.38
     znaczy
    -1.23
     czasem
    -1.20
    Station
    -1.19
     UIButton
    -1.18
     första
    -1.17
    簌
    -1.17
    ↵↵
    -1.17
    ᝰ
    -1.16
    امي
    -1.16
    POSITIVE LOGITS
     what
    1.44
     memoized
    1.39
    viser
    1.28
     Faced
    1.23
     Каждый
    1.23
    责编
    1.22
     Each
    1.21
    ibration
    1.20
     Monate
    1.19
     {
    1.18
    Activations Density 0.033%

    No Known Activations