© 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. 5999
    Prev
    Next
    INDEX
    Explanations

    9

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

    The neuron is detecting decimal numbers (floating-point numeric values) in the text.

    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
     I
    0.90
     a
    0.74
     cul
    0.74
     offend
    0.71
     Mechanic
    0.71
     No
    0.70
     Light
    0.70
    yc
    0.70
     exc
    0.70
     Src
    0.70
    POSITIVE LOGITS
    󠁿
    0.84
    咧
    0.83
    民众
    0.81
     идут
    0.81
    ClFN
    0.80
    ﻖ
    0.79
    王朝
    0.77
    ల్య
    0.77
    లై
    0.75
    aneity
    0.75
    Activations Density 0.000%

    No Known Activations