© 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. 13307
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on words that introduce suggestions or recommendations (e.g. “consider,” “think,” “allows”).

    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
    י
    0.79
    y
    0.78
     Fletcher
    0.78
     Lance
    0.73
    hle
    0.73
    ichael
    0.72
    sr
    0.70
    yat
    0.70
    k
    0.69
    ังก์ชัน
    0.69
    POSITIVE LOGITS
    重要的
    0.78
    ваны
    0.77
     умень
    0.76
    izadas
    0.75
     stained
    0.73
     rebuild
    0.73
     fáciles
    0.72
     meteen
    0.72
    ')+
    0.72
    ர்களின்
    0.72
    Activations Density 0.000%

    No Known Activations