© 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. 10-GEMMASCOPE-RES-131K
    7. 9329
    Prev
    Next
    INDEX
    Explanations

    Area followed by a descriptor

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

    The neuron flags multiword proper names—especially organization, place, or corporate names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     a
    -2.59
     for
    -1.95
    </h2>
    -1.49
     enten
    -1.44
     about
    -1.43
    </h4>
    -1.41
     in
    -1.36
       
    -1.35
    ">';
    -1.33
     péché
    -1.33
    POSITIVE LOGITS
     jednom
    1.70
    Comté
    1.70
    /***
    1.58
    了过来
    1.57
    Nazionale
    1.53
     aswell
    1.53
     habrían
    1.52
    Décès
    1.52
     Jeden
    1.48
     niektor
    1.48
    Activations Density 0.119%

    No Known Activations