© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4598
    Prev
    Next
    INDEX
    Explanations

    lists, items, tags, or categories

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

    The neuron fires strongly on numeric tokens and number‐related expressions (e.g. years, doses, counts).

    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
     sabbam
    0.80
     Informasi
    0.80
     HSPB
    0.79
     своего
    0.79
     Hodges
    0.75
     unitarity
    0.75
     Sadler
    0.74
    폿
    0.74
    unky
    0.73
    ிகளை
    0.73
    POSITIVE LOGITS
    ᴍ
    0.81
     முத
    0.81
     येते
    0.80
    TIL
    0.80
     reale
    0.79
    ZA
    0.79
    加えて
    0.76
     accidente
    0.76
     difer
    0.75
    mediate
    0.75
    Activations Density 0.001%

    No Known Activations