© 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. 10228
    Prev
    Next
    INDEX
    Explanations

    The neuron’s primary function is to detect occurrences of the word “important” (i.e. emphatic marker of importance).

    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
    सेवी
    1.09
     چ
    1.02
     tingling
    1.01
     deodor
    0.99
     Fiorent
    0.99
     Escol
    0.98
     assass
    0.98
    z
    0.97
     segu
    0.96
     dissatisf
    0.96
    POSITIVE LOGITS
    importance
    1.05
    ě
    1.05
    ેલ
    1.01
    ى
    1.01
     اهمیت
    0.98
     중요하다
    0.98
     importancia
    0.97
     importance
    0.96
     важно
    0.96
     penting
    0.92
    Activations Density 0.150%

    No Known Activations