© 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. 11824
    Prev
    Next
    INDEX
    Explanations

    eastern Ukraine

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

    The neuron fires on numeric sequences—especially decimal or floating‐point numbers (e.g. “435.8969,” “348.2048,” “351.999,” etc.).

    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
    ictions
    0.85
    irian
    0.84
    iring
    0.81
    opian
    0.79
    एनएल
    0.77
    atient
    0.76
    鬯
    0.76
    üne
    0.75
     আরে
    0.74
    toon
    0.73
    POSITIVE LOGITS
    include
    0.80
    >//
    0.75
    لاحظ
    0.75
    $/.
    0.74
     ]:
    0.74
     Veamos
    0.73
    ]//
    0.73
    #!/
    0.73
    \%$
    0.73
    affichage
    0.70
    Activations Density 0.007%

    No Known Activations