© 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. 3341
    Prev
    Next
    INDEX
    Explanations

    name, adoption, mixing

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

    The neuron selectively fires on tokens or spans composed of uppercase letter sequences (e.g. acronyms, headings, or all-caps 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
    е
    0.90
    fl
    0.84
    R
    0.82
    о
    0.79
    per
    0.79
    fer
    0.79
    ter
    0.77
    х
    0.77
    isem
    0.76
    ising
    0.76
    POSITIVE LOGITS
    Ⴌ
    0.87
     ලෙස
    0.82
    ນະ
    0.82
    utacji
    0.81
    处于
    0.79
    これで
    0.78
     tộc
    0.77
     infarction
    0.76
    至于
    0.76
     êtes
    0.75
    Activations Density 0.001%

    No Known Activations