© 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. 68612
    Prev
    Next
    INDEX
    Explanations

    requests and queries

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

    The neuron fires on words offering or facilitating services—especially modals and verbs like “can,” “assist,” “provide,” etc., used in customer-service or help contexts.

    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
     Kartu
    -0.84
     aż
    -0.77
    IORITY
    -0.75
     hume
    -0.75
    Ἔ
    -0.75
    Descri
    -0.75
     only
    -0.75
     affich
    -0.74
     تجاه
    -0.73
     ANNOUNC
    -0.73
    POSITIVE LOGITS
     requested
    2.17
     requests
    1.82
     request
    1.70
    Requested
    1.56
    requested
    1.52
     Requested
    1.32
     Request
    1.31
     requesting
    1.30
     Requests
    1.30
     queries
    1.25
    Activations Density 0.068%

    No Known Activations