© 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. 5275
    Prev
    Next
    INDEX
    Explanations

    psychological

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

    The neuron selectively activates on numeric tokens (years, section or citation numbers, and similar digits).

    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
     पिक्च
    0.76
     ennek
    0.74
    ﻁ
    0.74
    픈
    0.73
     Practices
    0.72
     Initiatives
    0.71
     Philosoph
    0.70
    芰
    0.70
     honoured
    0.69
    াস্থ্য
    0.68
    POSITIVE LOGITS
    ావ
    1.03
    bicycle
    0.81
    ERC
    0.78
    xxxxx
    0.77
     direita
    0.76
    ADO
    0.75
    لا
    0.73
    ఠ
    0.73
    ام
    0.72
    LOAD
    0.72
    Activations Density 0.000%

    No Known Activations