© 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. 77014
    Prev
    Next
    INDEX
    Explanations

    database relationships

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

    The neuron fires on programmer-defined identifiers—variable, method, class, or field names—in code snippets.

    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
    ILogger
    -0.83
    랐
    -0.83
     davran
    -0.82
     aguard
    -0.78
    рд
    -0.76
     lokalen
    -0.75
    就
    -0.75
     Haftung
    -0.75
    。“
    -0.75
    功夫
    -0.74
    POSITIVE LOGITS
    FK
    0.85
     Endless
    0.81
     cárcel
    0.81
     callous
    0.79
    שְׁ
    0.77
     którym
    0.76
    Ссылка
    0.75
    Id
    0.75
     ONLY
    0.75
    CrossRef
    0.74
    Activations Density 0.017%

    No Known Activations