© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3038
    Prev
    Next
    INDEX
    Explanations

    explanation

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

    The neuron strongly activates on the word “That,” especially when it begins a sentence or clause.

    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
     وهذه
    1.10
    ो
    1.06
    ী
    1.06
    ece
    1.02
    তে
    1.01
    een
    1.00
    ة
    0.99
    یه
    0.98
    กิจ
    0.91
    꾼
    0.91
    POSITIVE LOGITS
    それで
    1.76
     pesky
    1.71
    zelfde
    1.51
    日在
    1.20
    也
    1.20
    م
    1.16
    <0x8C>
    1.16
    样子
    1.16
     Karna
    1.12
     blushed
    1.12
    Activations Density 0.342%

    No Known Activations