© 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-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10509
    Prev
    Next
    INDEX
    Explanations

    years of or chickens

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

    The neuron fires strongly on proper names and other named‐entity tokens—i.e. specific people’s names, organization or location names, titles or acronyms.

    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_31_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
     riesgos
    0.63
     fundamentales
    0.60
    ldes
    0.58
    apadani
    0.57
     עד
    0.57
     fondamentale
    0.56
    esorios
    0.56
    욌
    0.56
     przechowy
    0.55
     سالم
    0.55
    POSITIVE LOGITS
     using
    0.59
     ourselves
    0.59
    Determine
    0.59
     First
    0.57
    First
    0.57
    Exact
    0.56
    Hmm
    0.54
     cliquant
    0.54
      
    0.54
    This
    0.53
    Activations Density 0.001%

    No Known Activations