© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39184
    Prev
    Next
    INDEX
    Explanations

    uniform weird disneyland

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

    The neuron detects common function words (high-frequency articles, pronouns, and conjunctions).

    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
     ✭✭
    -1.05
     negru
    -1.05
     TableColumn
    -1.02
     primit
    -1.00
     fumée
    -1.00
     枕
    -0.98
    قل
    -0.97
    </h3>
    -0.96
    (';
    -0.95
    Diabetes
    -0.95
    POSITIVE LOGITS
     longterm
    1.30
    Leírás
    1.09
    mvh
    1.01
     jūs
    0.99
    delingen
    0.98
     Если
    0.97
    mudah
    0.97
    Tämä
    0.96
     incomplète
    0.96
     saluti
    0.96
    Activations Density 1.304%

    No Known Activations