© 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. 14921
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly sensitive to the demonstrative “This,” especially when it appears as the first word of a sentence.

    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
     สถาน
    0.58
     Ши
    0.57
    いただき
    0.57
     Thị
    0.56
     Sébastien
    0.55
    をはじめ
    0.53
    鞑
    0.53
     スタ
    0.52
     Fonbet
    0.52
    Thông
    0.52
    POSITIVE LOGITS
     diminution
    0.54
     redirection
    0.52
     second
    0.50
     imply
    0.50
     exclusion
    0.50
     excludes
    0.50
     nonexistent
    0.50
     network
    0.49
     agent
    0.49
     precursor
    0.49
    Activations Density 0.000%

    No Known Activations