© 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. 95748
    Prev
    Next
    INDEX
    Explanations

    malformation, brimonidine, keratosis, RFID, scale

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

    scientific or medical terms in academic or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron fires on specialized domain-specific nouns and acronyms (e.g. disease names, protein or anatomical terms, technical scales and technologies).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    際に
    -1.46
     and
    -1.45
     this
    -1.36
     цьому
    -1.30
    ことも
    -1.30
    為に
    -1.29
    あー
    -1.27
    の概要
    -1.27
     этого
    -1.20
    ところに
    -1.20
    POSITIVE LOGITS
    もありますが
    1.18
    сора
    1.14
     岁
    1.12
    畝
    1.11
    ですので
    1.07
    ですが
    1.02
     شیپور
    1.01
    恚
    1.01
    gencias
    0.97
    Цитата
    0.97
    Activations Density 0.078%

    No Known Activations