© 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. 8397
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives ending in -est

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

    The neuron fires on superlative adjectives or adverbs formed with the “-est” ending.

    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
    า
    0.73
    ட்சத்திர
    0.71
     सीधा
    0.68
     недалеко
    0.68
    ップ
    0.66
     octahedral
    0.65
     whatnot
    0.65
     द्व
    0.64
    +}(
    0.64
     superhero
    0.64
    POSITIVE LOGITS
    รัฐ
    0.74
     realm
    0.70
     vše
    0.66
    просы
    0.66
     sekal
    0.63
     imaginable
    0.63
    꼭
    0.63
     mów
    0.63
    possible
    0.61
    সকল
    0.61
    Activations Density 0.007%

    No Known Activations