© 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. 10450
    Prev
    Next
    INDEX
    Explanations

    depending on

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

    The neuron triggers on multiword dependency expressions—verbs like “depending on” or “relying on” that signal one thing is contingent upon another.

    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
    chnung
    0.69
    ows
    0.68
    oure
    0.68
     Coefficient
    0.68
    eka
    0.66
    addy
    0.64
     👇
    0.64
    defaultValue
    0.64
    kka
    0.63
    方程
    0.61
    POSITIVE LOGITS
     motifs
    0.66
     темати
    0.63
     treatises
    0.62
     разнообраз
    0.62
     äußerst
    0.62
     sadistic
    0.62
     radeon
    0.61
     philanth
    0.61
    [*][[
    0.61
     tunable
    0.61
    Activations Density 0.001%

    No Known Activations