© 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. 22-GEMMASCOPE-RES-131K
    4. 11097
    Prev
    Next
    INDEX
    Explanations

    middle age, income, or stage

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

    The neuron strongly activates on occurrences of the word “middle.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     he
    -3.53
    ,
    -2.58
     ‘
    -2.58
     su
    -2.42
     to
    -2.41
    '
    -2.31
    >
    -2.27
     merkezi
    -2.25
    ↵↵
    -2.22
     –
    -2.16
    POSITIVE LOGITS
    鹟
    2.84
    most
    2.53
     selepas
    2.53
    鉨
    2.53
    ୌ
    2.48
     saveiro
    2.45
    quelize
    2.41
      【
    2.39
     élastique
    2.39
    推荐阅读
    2.38
    Activations Density 0.010%

    No Known Activations