© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95400
    Prev
    Next
    INDEX
    Explanations

    school lunches

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

    The neuron strongly activates on the standalone token “rid.”

    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
    子は
    -1.18
     všetky
    -1.17
     palma
    -1.12
    everything
    -1.09
     maquillage
    -1.07
    esor
    -1.05
     kaikki
    -1.05
     everything
    -1.03
     lahat
    -1.02
    middels
    -1.02
    POSITIVE LOGITS
     भी
    0.97
    了下来
    0.93
     reliever
    0.92
     L
    0.90
     caddy
    0.89
    zydent
    0.88
     vermin
    0.88
     and
    0.88
    ///</
    0.86
     H
    0.85
    Activations Density 0.000%

    No Known Activations