© 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. 34-GEMMASCOPE-RES-131K
    7. 99006
    Prev
    Next
    INDEX
    Explanations

    code constructs and operations

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

    This neuron identifies code declarations, especially C-style function definitions (e.g., the “static int __bam_safe_…” declaration).

    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
     bezw
    -1.02
    哈哈哈哈
    -0.93
     сына
    -0.88
    Cuts
    -0.87
     recientemente
    -0.86
     Қ
    -0.85
     erken
    -0.84
     lukisan
    -0.82
     Publicado
    -0.82
     zwier
    -0.81
    POSITIVE LOGITS
     check
    1.71
     maybe
    1.63
     get
    1.55
     calculate
    1.46
     determine
    1.44
    处理
    1.44
     find
    1.41
     do
    1.39
     adjust
    1.38
     prepare
    1.38
    Activations Density 0.043%

    No Known Activations