© 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. 10-GEMMASCOPE-RES-131K
    7. 105497
    Prev
    Next
    INDEX
    Explanations

    view controller initialization methods

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

    Objective-C code involving object allocation, initialization, or class instantiation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on capitalized identifiers in Objective-C code—especially class or type names (e.g. UIColor, AVQueuePlayer, InterfaceController).

    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
     to
    -2.47
     it
    -1.91
     when
    -1.81
     podían
    -1.67
     in
    -1.63
     with
    -1.63
     but
    -1.58
     vivía
    -1.56
     on
    -1.47
    แรก
    -1.46
    POSITIVE LOGITS
     ส์
    1.76
     trenes
    1.65
    ｕ
    1.54
    <blockquote>
    1.54
    sellors
    1.48
    绉
    1.47
     chré
    1.46
    UCION
    1.45
    Trying
    1.44
     dortmund
    1.44
    Activations Density 0.009%

    No Known Activations