© 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. 49440
    Prev
    Next
    INDEX
    Explanations

    titles and beginnings of lists

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

    The neuron is a high‐level “named-entity” detector, firing strongly on proper names (especially celebrities), titles, dates, and other capitalized entity tokens.

    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
     säger
    -1.01
     ایشان
    -0.94
    ถาม
    -0.90
     sql
    -0.84
     इसका
    -0.82
    '>{
    -0.81
    EndInit
    -0.81
     saying
    -0.81
     হয়
    -0.81
    setBounds
    -0.80
    POSITIVE LOGITS
    ınca
    0.89
     Etats
    0.87
    [,]
    0.85
    𝙢
    0.81
    ượ
    0.81
    yarakat
    0.80
     menegaskan
    0.79
    𝓶
    0.78
    Replicas
    0.78
    MLElement
    0.77
    Activations Density 0.020%

    No Known Activations