© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34375
    Prev
    Next
    INDEX
    Explanations

    also and additional information

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

    The neuron strongly activates on the word “also” (especially when it precedes another verb), i.e. it detects sentences adding supplemental information with “also.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    เริ่ม
    -1.23
     both
    -1.14
    んだから
    -1.09
     everything
    -1.09
     when
    -1.08
    both
    -1.07
     Semua
    -1.06
     originalen
    -1.02
    圖片來源
    -1.01
     Masalah
    -1.01
    POSITIVE LOGITS
     features
    1.18
     social
    1.05
     sub
    1.05
     special
    1.03
     flexibility
    1.02
    の人に
    1.01
    casm
    1.00
     crucial
    0.99
    的道
    0.99
     kasama
    0.98
    Activations Density 0.051%

    No Known Activations