© 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. 34-GEMMASCOPE-RES-131K
    4. 116547
    Prev
    Next
    INDEX
    Explanations

    pop in to store

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

    The neuron detects calls to action inviting a visit, especially the phrase “pop in.”

    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
     AGENTS
    -0.74
    zzi
    -0.74
    wart
    -0.73
    Unary
    -0.70
    Esc
    -0.70
    cheon
    -0.70
    listeners
    -0.70
     as
    -0.69
    sek
    -0.68
    ār
    -0.67
    POSITIVE LOGITS
     inst
    3.30
     store
    3.05
     stores
    2.66
    store
    2.22
    Store
    2.08
     Store
    2.06
    店内
    2.03
    inst
    1.99
    STORE
    1.87
     Stores
    1.82
    Activations Density 0.047%

    No Known Activations