© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9474
    Prev
    Next
    INDEX
    Explanations

    Objective-C initWithFrame calls

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

    The neuron fires on Objective-C initializer method names (e.g. “initWithFrame”).

    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
    1
    -3.95
    2
    -3.89
    en
    -3.89
    9
    -3.77
    a
    -3.72
    d
    -3.64
    5
    -3.64
    7
    -3.59
    3
    -3.47
    This
    -3.42
    POSITIVE LOGITS
    𐄁
    2.86
    sandalia
    2.73
    岽
    2.70
    ჻
    2.64
     márm
    2.63
    欤
    2.50
    犼
    2.47
    
    2.42
    ፨
    2.42
    bbt
    2.42
    Activations Density 0.000%

    No Known Activations