© 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. 7077
    Prev
    Next
    INDEX
    Explanations

    Bathroom Grille, Science Centre

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

    The neuron fires strongly on capitalized proper names and titles (e.g. organization names, license headings, class or project names, song/movie titles).

    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
     mainly
    -0.84
     причиной
    -0.80
     came
    -0.79
     Similar
    -0.79
     more
    -0.77
     oh
    -0.75
     £
    -0.75
     There
    -0.74
     Scientists
    -0.74
     two
    -0.73
    POSITIVE LOGITS
     boomers
    0.91
     Inks
    0.89
    nání
    0.88
    ']]
    0.87
    דש
    0.86
     BIR
    0.85
     nukes
    0.85
    캔
    0.84
    施行
    0.84
     Soprano
    0.84
    Activations Density 0.161%

    No Known Activations