© 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. 4998
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on the phrase “want to,” flagging expressions of desire or intent.

    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
    y
    1.09
    та
    1.02
     cataly
    0.99
     analyzing
    0.91
    ي
    0.89
    י
    0.84
     personnel
    0.82
     catalyzes
    0.80
    І
    0.80
     physical
    0.78
    POSITIVE LOGITS
    europe
    0.94
     habido
    0.93
    ígono
    0.92
    effetto
    0.91
     razy
    0.86
    ectady
    0.86
    CONH
    0.86
     veces
    0.86
    ჲ
    0.86
    知道
    0.85
    Activations Density 0.076%

    No Known Activations