© 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. 31-GEMMASCOPE-2-RES-16K
    7. 393
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to positive evaluative adjectives (e.g. good, best, great, beautiful, wonderful).

    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
     $\
    0.25
     atau
    0.24
    }/
    0.23
     più
    0.23
     Atau
    0.23
     More
    0.22
     "\\
    0.22
     veya
    0.22
    `
    0.22
    ){
    0.22
    POSITIVE LOGITS
     esimerk
    0.41
     exemples
    0.40
     exemplos
    0.38
     examples
    0.38
     motivator
    0.38
     accomplishments
    0.36
     performers
    0.36
     contenders
    0.36
     example
    0.36
     voorbeeld
    0.36
    Activations Density 1.180%

    No Known Activations