© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2640
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on occurrences of the word “there.”

    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
     harmful
    0.69
     copyright
    0.67
    И
    0.67
    nya
    0.66
     harmony
    0.65
     sebuah
    0.65
     an
    0.64
    ราะห์
    0.63
    s
    0.63
     eau
    0.63
    POSITIVE LOGITS
    abouts
    0.97
    简直
    0.72
    comes
    0.67
     ナイス
    0.66
    ੋ
    0.66
     हैं
    0.65
    ل
    0.65
    ੂੰ
    0.65
     Started
    0.65
    ਾਰੇ
    0.64
    Activations Density 0.000%

    No Known Activations