© 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. 22-GEMMASCOPE-RES-131K
    7. 13761
    Prev
    Next
    INDEX
    Explanations

    lead-in to descriptive clauses

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

    The neuron fires on map‐rendering terms, in particular the mention of “roads” and color words like “blue.”

    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
    Ưu
    -1.28
    士兵
    -1.25
    🥎
    -1.24
     methods
    -1.23
     method
    -1.21
     easy
    -1.20
     оружи
    -1.17
     Internasional
    -1.16
    centerTitle
    -1.16
    đại
    -1.16
    POSITIVE LOGITS
     després
    1.12
    नि
    1.02
     Faktoren
    0.99
     primero
    0.99
     prioridad
    0.98
    主題
    0.98
     häufiger
    0.98
    瞬間
    0.98
    ถึง
    0.97
     primeiro
    0.96
    Activations Density 0.000%

    No Known Activations