© 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. 15836
    Prev
    Next
    INDEX
    Explanations

    This neuron detects occurrences of the word “mechanical” (as in “electronic or mechanical”).

    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
    ように
    0.95
    いに
    0.95
    widths
    0.90
    stüt
    0.88
    蚪
    0.88
     vínculos
    0.86
     significado
    0.84
    linewidth
    0.84
     สําหรับ
    0.84
     positivos
    0.83
    POSITIVE LOGITS
    ﻴ
    0.98
     April
    0.90
    9
    0.90
     October
    0.88
     or
    0.88
    an
    0.87
    ל
    0.86
    EE
    0.85
     Voici
    0.85
     February
    0.82
    Activations Density 0.001%

    No Known Activations