© 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. 4685
    Prev
    Next
    INDEX
    Explanations

    color

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

    This neuron fires on tokens that are part of numerical or quantitative expressions (e.g. numbers, measurements, percentages, counts).

    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
     ukaz
    0.87
     hayat
    0.86
    hiyam
    0.86
     conhecer
    0.86
    idel
    0.85
     Еўропы
    0.84
    ﻢ
    0.84
     compartilhar
    0.83
     тұ
    0.81
    krét
    0.81
    POSITIVE LOGITS
     Developer
    0.70
    ِن
    0.69
     Industrie
    0.65
    ៊ី
    0.65
    ័រ
    0.65
     ReactDOM
    0.64
     config
    0.64
    ]));
    0.63
    ِل
    0.63
     Technische
    0.63
    Activations Density 0.001%

    No Known Activations