© 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. 130966
    Prev
    Next
    INDEX
    Explanations

    The neuron spotlights programming identifiers (e.g. function names, class or type names, and namespace paths).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    programming language keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    bedded
    -1.10
     prenant
    -1.05
     אותם
    -0.94
     vó
    -0.93
    wered
    -0.92
     gratuits
    -0.90
     venant
    -0.90
     حکومت
    -0.90
     relojes
    -0.89
     dè
    -0.88
    POSITIVE LOGITS
     []:
    1.10
     first
    1.05
     provavelmente
    1.03
     deixou
    0.97
     wykor
    0.94
     explicou
    0.93
     respondeu
    0.92
     Vereinig
    0.92
     perguntou
    0.91
     Probably
    0.91
    Activations Density 0.143%

    No Known Activations