© 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. 24-GEMMASCOPE-2-RES-16K
    4. 5969
    Prev
    Next
    INDEX
    Explanations

    careful scrutiny and subsequent action

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

    Neuron 4 fires strongly on two-word phrasal-verb chunks (a verb plus its following particle/preposition), such as “send in,” “take out,” “drop off,” or “bring in.”

    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
     возника
    0.72
    abilità
    0.70
    uların
    0.68
    ňuje
    0.68
     éxito
    0.67
     возник
    0.66
    颖
    0.66
     допусти
    0.65
    ailability
    0.64
     menyatakan
    0.64
    POSITIVE LOGITS
     tuck
    0.73
     একটু
    0.71
     kde
    0.70
    surgery
    0.67
     soak
    0.64
     ಡ
    0.64
     좀
    0.64
     scrubbing
    0.64
     lick
    0.63
    좀
    0.63
    Activations Density 0.182%

    No Known Activations