© 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. 16244
    Prev
    Next
    INDEX
    Explanations

    banking and political entities

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

    The neuron fires on tokens that contain or begin with uppercase letters—e.g. proper nouns, section headings, acronyms, and other capitalized 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
    ul
    1.15
    s
    1.10
    re
    1.09
    sh
    0.95
    d
    0.91
    lös
    0.90
    lad
    0.88
    ör
    0.85
    sas
    0.84
    l
    0.84
    POSITIVE LOGITS
     livré
    0.91
    যুদ্ধ
    0.89
    щении
    0.88
     heyday
    0.83
     verpflichtet
    0.83
    ᱗
    0.83
     anmelden
    0.82
     kısmı
    0.81
     Combien
    0.81
     cometido
    0.80
    Activations Density 0.001%

    No Known Activations