© 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. 10874
    Prev
    Next
    INDEX
    Explanations

    related among glimpse character

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

    the neuron activates on floating‐point number tokens (decimal numbers with a dot) 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
    пло
    0.83
    ে
    0.77
     Dienste
    0.77
    ੀ
    0.75
     Дмитри
    0.75
    burnt
    0.73
    dropped
    0.72
    ℗
    0.72
    굶
    0.72
    }$-
    0.71
    POSITIVE LOGITS
     lớn
    0.84
     toolPath
    0.79
     eval
    0.79
     oldCount
    0.76
     protagonista
    0.74
     valida
    0.73
     sawtooth
    0.72
     brillo
    0.71
    峥
    0.71
     læng
    0.70
    Activations Density 0.000%

    No Known Activations