© 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. 142
    Prev
    Next
    INDEX
    Explanations

    medical departments, tracking, library, store

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

    locations in a facility where services are provided, such as "address bar," "emergency department," "sick bed," and "notification bar."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron identifies mentions of specific locations or place‐names (e.g. “address bar,” “sick bed,” “emergency department”).

    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
    が
    -1.05
    </strong>
    -1.05
    Another
    -1.02
     }{@
    -0.99
    jeux
    -0.98
    Both
    -0.95
    })()
    -0.94
     Muñoz
    -0.94
    別の
    -0.93
    protoimpl
    -0.93
    POSITIVE LOGITS
     department
    1.48
     section
    1.19
    inheit
    1.01
     center
    1.01
     page
    1.00
    了许多
    1.00
     committee
    1.00
     فلسط
    0.98
    desliz
    0.98
    renaline
    0.96
    Activations Density 0.097%

    No Known Activations