© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106874
    Prev
    Next
    INDEX
    Explanations

    directory paths, vendor, modules, repository, gems

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

    This neuron activates on filesystem path components (e.g. directory names, module/package paths, and separators).

    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
    会议
    -0.82
    ]+=
    -0.75
    ТЕЛЬ
    -0.75
    會議
    -0.75
    '],
    -0.74
    大量
    -0.74
    *)
    -0.74
    Ộ
    -0.73
     orth
    -0.73
     meeting
    -0.72
    POSITIVE LOGITS
     Meski
    0.84
     Ternyata
    0.81
    probieren
    0.81
    运动员
    0.81
     samedi
    0.81
     Seperti
    0.79
    examples
    0.78
    你能
    0.78
     usando
    0.77
     Langkah
    0.77
    Activations Density 0.003%

    No Known Activations