© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13001
    Prev
    Next
    INDEX
    Explanations

    guess what comes next

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

    This neuron strongly activates on proper names and other named-entity tokens (titles, place names, brands, etc.).

    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
     extrema
    0.71
    ខ
    0.64
     plaque
    0.64
     Field
    0.63
     FORCE
    0.63
     manger
    0.61
     fl
    0.60
     পার
    0.60
     force
    0.60
    జ్‌
    0.60
    POSITIVE LOGITS
    س
    0.91
    ྙ
    0.89
     ejes
    0.88
     mensuales
    0.85
     mieszkań
    0.84
    inking
    0.82
     siento
    0.82
     enemigos
    0.82
    ě
    0.81
    ̌
    0.80
    Activations Density 0.000%

    No Known Activations