© 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. 10-GEMMASCOPE-RES-131K
    4. 99591
    Prev
    Next
    INDEX
    Explanations

    optional types in code

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

    The neuron fires on type declarations with “?” or “!” (i.e. optional or implicitly unwrapped types).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     męska
    -1.61
     kwamba
    -1.48
     sooooo
    -1.47
     mwenye
    -1.45
    gucigalpa
    -1.43
     utterly
    -1.43
     Meningkatkan
    -1.41
     Like
    -1.39
     TWO
    -1.38
     supremely
    -1.38
    POSITIVE LOGITS
    ⡂
    1.72
     innych
    1.66
     he
    1.58
     l
    1.53
     dando
    1.51
    ".$_
    1.48
    fahan
    1.47
     al
    1.45
     pivotal
    1.45
    preferably
    1.44
    Activations Density 0.001%

    No Known Activations