© 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. 22-GEMMASCOPE-RES-131K
    7. 104754
    Prev
    Next
    INDEX
    Explanations

    particularly to

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

    The neuron responds to small function words that refer back or qualify earlier content—especially pronouns (it, them, your), simple adverbs (once, back, particularly), and similar anaphoric/qualifying terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    αρα
    -1.02
    จะมี
    -0.97
    ⴷ
    -0.95
     rapidement
    -0.94
     télécommande
    -0.93
     NgModule
    -0.92
    iuo
    -0.91
     lâmpada
    -0.90
     Kamb
    -0.90
    şme
    -0.90
    POSITIVE LOGITS
    likation
    0.95
    ings
    0.88
    !
    0.85
    updater
    0.82
    ueves
    0.82
    ometry
    0.81
     зае
    0.81
     例
    0.80
     أيضاً
    0.80
    Referências
    0.78
    Activations Density 0.130%

    No Known Activations