© 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. 11742
    Prev
    Next
    INDEX
    Explanations

    characterized by

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

    The neuron fires on the word “determined.”

    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
    ުޅ
    1.01
     toplum
    0.90
     топлива
    0.89
     уйнау
    0.88
     chimique
    0.86
    ﻢ
    0.86
     deputado
    0.84
    álu
    0.82
     gostaria
    0.82
    amélioration
    0.82
    POSITIVE LOGITS
    er
    0.77
     chief
    0.77
    h
    0.75
     color
    0.75
     antiseptic
    0.73
    ter
    0.72
     defense
    0.72
     allowance
    0.71
     odor
    0.71
    dex
    0.71
    Activations Density 0.000%

    No Known Activations