© 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. 10024
    Prev
    Next
    INDEX
    Explanations

    connection to

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

    The neuron fires on words that express linking or relating one thing to another (e.g., connect, correlate, associate).

    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
     Ants
    1.36
     nurtured
    1.16
     episcopal
    1.12
    氶
    1.12
     ethnographic
    1.11
     Anger
    1.11
    으로써
    1.08
    бра
    1.07
     scler
    1.07
    ussie
    1.07
    POSITIVE LOGITS
    กับการ
    1.63
    กับ
    1.62
    am
    1.59
     dangere
    1.57
    er
    1.53
    о
    1.45
    w
    1.45
    te
    1.42
    AKS
    1.41
    ா
    1.41
    Activations Density 4.923%

    No Known Activations