© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130748
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on descriptive modifier words (adjectives).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    adjectives and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    をしました
    -1.51
     funguje
    -1.48
     so
    -1.48
    になりました
    -1.43
    の準備
    -1.41
     awfully
    -1.38
    ができます
    -1.38
     versiones
    -1.37
     trajes
    -1.37
     plataformas
    -1.37
    POSITIVE LOGITS
     of
    2.64
    などの
    1.36
    を
    1.34
    ของ
    1.34
     الرغم
    1.27
    of
    1.25
     tages
    1.23
     особенно
    1.18
     is
    1.16
    など
    1.16
    Activations Density 0.014%

    No Known Activations