© 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. 10-GEMMASCOPE-RES-131K
    4. 57365
    Prev
    Next
    INDEX
    Explanations

    moons and satellites

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

    The neuron fires on mentions of moons (natural satellites) and related numerical or descriptive details about them.

    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
     zumal
    -1.35
    re
    -1.30
     チェック
    -1.30
     was
    -1.25
    ."
    -1.22
     Hinblick
    -1.20
    一部
    -1.20
    le
    -1.17
     zarówno
    -1.17
     same
    -1.16
    POSITIVE LOGITS
    鎢
    1.60
     bonté
    1.48
    ( ̄
    1.48
     októ
    1.44
     cruzado
    1.43
    围绕
    1.41
     with
    1.38
    Fär
    1.35
    (゚
    1.35
    企业的
    1.35
    Activations Density 0.026%

    No Known Activations