© 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. 13012
    Prev
    Next
    INDEX
    Explanations

    installation and setup

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

    The neuron is highly activated by occurrences of “up,” especially in phrasal verbs and the word “setup.”

    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
     अलावा
    0.93
     ，
    0.87
    それぞれの
    0.84
    eduanya
    0.84
    ν
    0.83
    ubehör
    0.82
    ８
    0.82
    ۸
    0.81
    ۷
    0.81
     それぞれ
    0.80
    POSITIVE LOGITS
     commence
    0.91
     tzv
    0.89
     procuring
    0.89
     prenez
    0.88
     frustrations
    0.88
     mechanized
    0.88
     liquidation
    0.86
    นั่ง
    0.85
     dinn
    0.84
     randomize
    0.84
    Activations Density 4.284%

    No Known Activations