© 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. 48081
    Prev
    Next
    INDEX
    Explanations

    professional practice and graduates

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

    The neuron highlights individual list items or enumerated phrases (e.g. reasons, requirements, or steps) in a comma- or conjunction-separated series.

    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
     ORGAN
    -0.78
     departament
    -0.77
    زان
    -0.76
     Behavioural
    -0.75
     splendour
    -0.74
     ORGANIC
    -0.74
    Mitsubishi
    -0.73
     CSIRO
    -0.73
     oliver
    -0.73
    ઈ
    -0.73
    POSITIVE LOGITS
     fitness
    1.20
     practice
    1.06
     Fitness
    1.05
    Fitness
    1.02
    fitness
    1.01
     FTP
    0.97
     regist
    0.97
     Practice
    0.88
     practitioner
    0.86
    practice
    0.84
    Activations Density 0.009%

    No Known Activations