© 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. 34-GEMMASCOPE-RES-131K
    7. 60201
    Prev
    Next
    INDEX
    Explanations

    compact() and resolve()

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

    This neuron detects programming identifier tokens—names of functions, methods, parameters, directives, etc., in code snippets.

    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
    omiast
    -0.93
    heute
    -0.91
    FromString
    -0.82
    podob
    -0.81
    spiele
    -0.81
    hanno
    -0.79
     viena
    -0.76
     söyl
    -0.75
    ग़
    -0.75
     хочешь
    -0.74
    POSITIVE LOGITS
     compact
    1.88
    compact
    1.51
     Compact
    1.28
    Compact
    1.26
     компакт
    1.19
     compactness
    1.07
    locals
    1.05
     compacto
    1.03
     locals
    1.01
    コンパクト
    0.99
    Activations Density 0.003%

    No Known Activations