© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4638
    Prev
    Next
    INDEX
    Explanations

    ongoing persecution

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

    The neuron strongly activates on numeric tokens—e.g. digits, percentages, and other number expressions.

    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
    વે
    0.88
    ppies
    0.88
    unks
    0.82
    asures
    0.80
     condos
    0.79
    م
    0.79
     tonnes
    0.78
    oons
    0.77
    estries
    0.77
    ج
    0.76
    POSITIVE LOGITS
    อัน
    0.91
     Minority
    0.84
    }
    0.83
    και
    0.78
    ให้กับ
    0.78
     อำ
    0.77
     εν
    0.77
     충
    0.76
     Rfe
    0.74
     สุด
    0.73
    Activations Density 0.000%

    No Known Activations