© 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. 81541
    Prev
    Next
    INDEX
    Explanations

    Apple (Objective-C/Swift) code snippets

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

    This neuron activates on the tokens making up Objective-C method signatures (the “- (…)" or “+ (…)" declarations and their method-name-with-colon parts).

    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
     both
    -1.10
     if
    -1.02
     even
    -1.02
     sowohl
    -1.01
     with
    -0.93
    NSDate
    -0.92
    UIAlert
    -0.90
    hoja
    -0.89
    ながらも
    -0.89
    高效
    -0.83
    POSITIVE LOGITS
    id
    1.16
     id
    1.13
    nullable
    1.02
     nullable
    1.02
    void
    0.98
     lác
    0.94
     delightful
    0.91
    __
    0.91
     fabulous
    0.90
    页面存档备份
    0.90
    Activations Density 0.012%

    No Known Activations