© 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. 59568
    Prev
    Next
    INDEX
    Explanations

    software frameworks and libraries

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

    The neuron fires on tokens that come from documentation or README‐style descriptive text (e.g. package summaries and comment headers) rather than code.

    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
     this
    -1.13
    した場合
    -0.98
    を行いました
    -0.93
    ﹔
    -0.93
     această
    -0.93
     Через
    -0.90
     when
    -0.89
     Estudio
    -0.89
     rând
    -0.88
     Politique
    -0.87
    POSITIVE LOGITS
    ributed
    1.12
     sane
    1.05
    Damn
    1.02
    replacement
    1.00
     помогут
    1.00
     patrones
    0.98
     hızlı
    0.97
     batteries
    0.96
     projeto
    0.96
     cucharadita
    0.96
    Activations Density 0.282%

    No Known Activations