© 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. 73858
    Prev
    Next
    INDEX
    Explanations

    list structure indicators

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

    The neuron strongly activates on programming‐language identifier tokens (like variable or function names such as “cheat” or “Wire”).

    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
     statistik
    -1.14
     maksi
    -1.08
    esist
    -1.02
     maksimal
    -0.98
    り物
    -0.97
    нија
    -0.96
     hakim
    -0.94
     pulsa
    -0.94
    stasi
    -0.90
     vagyok
    -0.90
    POSITIVE LOGITS
     pleasurable
    0.93
     этими
    0.92
     drew
    0.92
     jenen
    0.91
    였다
    0.91
     queste
    0.91
    这些
    0.88
    垫
    0.88
     agonizing
    0.88
     meager
    0.86
    Activations Density 0.003%

    No Known Activations