© 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. 130989
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on Objective-C method declarations, specifically the parenthesized return-type tokens like “instancetype” or “id” in class interface/implementation signatures.

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

    Objective-C initializers and types

    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
     Stoffe
    -1.24
     encantador
    -1.18
     a
    -1.13
     aguj
    -1.13
     unicórnio
    -1.11
    がありません
    -1.10
     escritores
    -1.09
     férias
    -1.09
     veröffentlich
    -1.06
     désolés
    -1.05
    POSITIVE LOGITS
    </strong>
    1.59
     igång
    1.18
    </h1>
    1.16
    Achter
    1.15
    ñora
    1.15
     do
    1.14
    」，
    1.13
     Manuscripts
    1.10
     esimer
    1.08
     toimi
    1.08
    Activations Density 0.003%

    No Known Activations