© 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. 6285
    Prev
    Next
    INDEX
    Explanations

    nickname or character name

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

    The neuron strongly activates on uncommon or specialized content tokens—especially named entities, legal/technical terms, and other infrequent words.

    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
     elapsed
    0.71
     недоста
    0.64
     penalized
    0.64
    ور
    0.63
    ﴿
    0.63
    ім
    0.63
    ون
    0.63
     адво
    0.62
     commemorated
    0.62
    ت
    0.62
    POSITIVE LOGITS
    mathbf
    1.13
    osition
    0.90
    ⺈
    0.85
    lobe
    0.83
     కలిగి
    0.82
     Skye
    0.81
     หมาย
    0.80
    quela
    0.79
    ObjectUnderTest
    0.79
    恴
    0.79
    Activations Density 0.000%

    No Known Activations