© 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. 59304
    Prev
    Next
    INDEX
    Explanations

    objective C or objective of

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

    The main thing this neuron does is detect occurrences of the programming‐language name “Objective-C.”

    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
     erhielten
    -1.18
     реализации
    -1.02
     gehör
    -0.95
    Ꮞ
    -0.93
    zös
    -0.93
    arreglo
    -0.93
    sodik
    -0.91
     linken
    -0.91
     emphatically
    -0.90
     mußten
    -0.89
    POSITIVE LOGITS
     Objective
    1.17
    Objective
    1.17
    objective
    1.05
     reass
    1.05
     verifiable
    0.99
     объек
    0.98
    obj
    0.98
    objec
    0.96
     Obj
    0.96
     Objectives
    0.93
    Activations Density 0.020%

    No Known Activations