© 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. 8422
    Prev
    Next
    INDEX
    Explanations

    year count

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

    The neuron strongly activates on floating‐point numeric tokens (numbers with decimal points).

    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
    Ι
    0.82
     convertir
    0.75
     βα
    0.75
    Ş
    0.71
    ptr
    0.70
    BROOK
    0.70
    ILE
    0.69
    R
    0.68
     অমিত
    0.68
    ብዙ
    0.68
    POSITIVE LOGITS
    ból
    0.80
    ങ്ങി
    0.75
     চলিয়া
    0.74
    ﻝ
    0.74
     operacional
    0.72
    半島
    0.72
    சிரியர்
    0.72
     Gosudarstvennyj
    0.72
     impede
    0.71
    Stages
    0.71
    Activations Density 0.000%

    No Known Activations