© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3298
    Prev
    Next
    INDEX
    Explanations

    list construction; structured information

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

    the neuron responds to technical labels and identifiers such as acronyms, version numbers, and similar proper‐name tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kongo
    0.40
    thia
    0.37
     yac
    0.36
     строительства
    0.35
     hert
    0.35
    рь
    0.34
    0
    0.34
    ObjectId
    0.33
     Tol
    0.33
     camer
    0.33
    POSITIVE LOGITS
     Guidelines
    0.50
    पेक्ष
    0.48
     Listings
    0.47
     전문가
    0.46
     booklet
    0.44
    Guidelines
    0.44
     உதவு
    0.44
    📩
    0.44
     Websites
    0.43
    スナー
    0.43
    Activations Density 0.000%

    No Known Activations