© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117656
    Prev
    Next
    INDEX
    Explanations

    Kotlin specific syntax

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

    This neuron detects programming‐language syntax tokens—especially assignment and declaration symbols (like “=”, “val”, “fun”, braces, etc.) typical of Kotlin/Java code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     särsk
    -0.79
    uzzi
    -0.73
    вот
    -0.72
    SSD
    -0.72
     Cronin
    -0.71
    因为
    -0.71
    ()])
    -0.69
     Lut
    -0.69
    NSIndexPath
    -0.68
    patrón
    -0.68
    POSITIVE LOGITS
     ?:
    1.86
    ?:
    1.18
     let
    0.94
    瑜
    0.94
     mutable
    0.93
    OrNull
    0.88
     nullable
    0.88
    checkNotNull
    0.81
     :-
    0.79
     tambien
    0.78
    Activations Density 0.028%

    No Known Activations