© 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. 7702
    Prev
    Next
    INDEX
    Explanations

    time periods

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

    The neuron selectively responds to numeric tokens—especially decimal‐formatted numbers and statistical values.

    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
     говорит
    0.96
    ARON
    0.91
    Honestly
    0.84
     detección
    0.82
    에
    0.82
     じゃん
    0.81
    embra
    0.80
    Α
    0.79
     autorización
    0.79
     जिद
    0.77
    POSITIVE LOGITS
     monasteries
    0.85
     prosperity
    0.80
     Telephone
    0.80
    νης
    0.79
     perennials
    0.79
     Multiplication
    0.75
     Malam
    0.75
     Norm
    0.75
     Sangh
    0.75
     lama
    0.74
    Activations Density 0.000%

    No Known Activations