© 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. 4854
    Prev
    Next
    INDEX
    Explanations

    custom, using, required

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

    The neuron strongly activates on numeric tokens—especially decimal or floating‐point numbers.

    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
    ﻥ
    0.86
     accrued
    0.81
     তথাপি
    0.77
     बैठे
    0.75
     поз
    0.73
    гне
    0.73
    ยนต์
    0.72
     accruing
    0.71
     desco
    0.71
     valorar
    0.71
    POSITIVE LOGITS
     Adriano
    0.82
    "></
    0.79
    wt
    0.78
     этот
    0.78
     Shaft
    0.77
    ew
    0.76
    ateľ
    0.74
    i
    0.74
    りん
    0.73
    this
    0.72
    Activations Density 0.000%

    No Known Activations