© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1599
    Prev
    Next
    INDEX
    Explanations

    free or free-related terms

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

    The neuron fires on the word “Free” when used as a promotional offer label.

    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_31_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
    rownames
    0.66
    Ⲗ
    0.64
    密钥
    0.63
    AxisSize
    0.62
    ljena
    0.59
    ljenje
    0.59
     Pavia
    0.59
    이크
    0.58
     কলিকাতা
    0.58
    IVOS
    0.57
    POSITIVE LOGITS
     Free
    1.37
    🆓
    1.21
     free
    1.18
    Free
    1.16
     ফ্রি
    1.16
     freer
    1.10
     libre
    1.09
    free
    1.08
     फ्री
    1.07
    bies
    1.05
    Activations Density 0.206%

    No Known Activations