© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73063
    Prev
    Next
    INDEX
    Explanations

    listing various items

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

    The neuron fires on occurrences of the word “list.”

    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
    WILL
    -0.97
     medlemmer
    -0.96
     cukru
    -0.92
    angat
    -0.85
    ReferenceEquals
    -0.84
    nextProps
    -0.84
    designated
    -0.84
     conclusione
    -0.82
    Geographie
    -0.82
    mik
    -0.82
    POSITIVE LOGITS
     available
    1.27
     who
    1.13
     offered
    1.10
    严重的
    1.06
     list
    1.01
     information
    1.01
    有哪些
    0.97
     neler
    0.96
     different
    0.91
     what
    0.90
    Activations Density 0.042%

    No Known Activations