© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10323
    Prev
    Next
    INDEX
    Explanations

    friendly

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

    The neuron identifies highly positive, praising adjectives (e.g. beautiful, lovely, helpful) indicating favorable sentiment.

    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
    ください
    1.05
    ς
    1.00
    a
    0.93
    ния
    0.91
    ة
    0.91
    s
    0.90
    نك
    0.89
    element
    0.87
     рядом
    0.86
    麼
    0.85
    POSITIVE LOGITS
     transpired
    0.88
    \">
    0.75
    icions
    0.73
     forested
    0.70
    णाल
    0.70
    {\"
    0.69
    ienen
    0.68
    ockets
    0.68
    😌
    0.68
     constituted
    0.65
    Activations Density 0.045%

    No Known Activations