© 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. 79731
    Prev
    Next
    INDEX
    Explanations

    code block structure

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

    This neuron spotlights code identifiers written in CamelCase or PascalCase (e.g. React component or prop/type 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
     enligt
    -1.09
     for
    -1.09
    if
    -1.05
     vitales
    -1.02
    歩いて
    -1.02
     agreeable
    -1.01
    陡
    -0.99
    i
    -0.97
    ua
    -0.96
    j
    -0.96
    POSITIVE LOGITS
     soggior
    1.37
     recent
    1.11
     ricevere
    1.10
     affez
    1.08
    回来了
    1.05
     Auseinander
    1.04
     utilizz
    1.03
    dée
    1.03
    狀態
    1.02
    hasilkan
    1.02
    Activations Density 0.001%

    No Known Activations