© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8947
    Prev
    Next
    INDEX
    Explanations

    interface interaction, component, language

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

    the neuron responds to standalone numeric tokens, especially those marking years or citation numbers in references.

    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
     sesuai
    0.88
    ある
    0.84
    TERS
    0.79
    ो
    0.79
    0.79
     Oeste
    0.78
     dicen
    0.76
    计时
    0.75
     enteral
    0.75
    测
    0.75
    POSITIVE LOGITS
     Количество
    0.75
     великолеп
    0.72
     баскетбол
    0.72
     Fähigkeiten
    0.66
     компонен
    0.65
     Weltkrieg
    0.65
    段階
    0.64
     пространства
    0.64
     взаимодействие
    0.64
     framework
    0.63
    Activations Density 0.001%

    No Known Activations