© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9888
    Prev
    Next
    INDEX
    Explanations

    LLMs, AI, RX, clothing, lunch, Gucci

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is detecting hashtag tokens (words prefixed with “#”).

    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_31_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
     Beberapa
    0.75
     〢
    0.73
     OFFICIAL
    0.70
    ⁩
    0.69
    adari
    0.66
     Сергея
    0.66
     Fungsi
    0.66
    Official
    0.66
    imbangan
    0.66
     Issues
    0.65
    POSITIVE LOGITS
    shorts
    0.66
    instagood
    0.61
    stays
    0.61
    nof
    0.55
    fyp
    0.54
    ↵↵
    0.53
    出会
    0.53
    TimeTo
    0.53
    ecommerce
    0.52
     instantiate
    0.51
    Activations Density 0.007%

    No Known Activations