© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71787
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs or nouns

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

    The neuron flags passages describing sports match outcomes, especially numeric fight results and competitor names.

    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
     mentiras
    -1.36
    也将
    -1.14
     those
    -1.14
    悖
    -1.13
    dominal
    -1.13
     resalt
    -1.13
     verdadera
    -1.13
     Bestimm
    -1.11
    FOREWORD
    -1.10
     auténtica
    -1.08
    POSITIVE LOGITS
     dieß
    1.22
    ポケモン
    1.16
     défauts
    1.16
     vœux
    1.13
     墊
    1.13
    アイテム
    1.13
     parfums
    1.05
     bricola
    1.05
     Mø
    1.05
     praticamente
    1.05
    Activations Density 0.141%

    No Known Activations