© 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. 10-GEMMASCOPE-RES-131K
    4. 105470
    Prev
    Next
    INDEX
    Explanations

    craniofacial, cranial bone, cranium, cranked

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

    The neuron detects variations of the word "cranio" and related anatomical terms in scientific and medical contexts.

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

    The neuron is a detector for the letter sequence “cran” (i.e. subwords or prefixes containing “cran”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     But
    -3.00
    냑
    -2.48
    eterangan
    -2.44
    でも
    -2.36
    瑧
    -2.36
     verwendeten
    -2.34
    ↵↵
    -2.31
    鴒
    -2.27
          
    -2.22
     they
    -2.19
    POSITIVE LOGITS
    鶺
    2.92
    ጺ
    2.92
    鸶
    2.89
    ‪.‬‬
    2.81
    と書
    2.72
     laiss
    2.55
     catholic
    2.42
     détach
    2.41
     possibles
    2.41
     så
    2.36
    Activations Density 0.006%

    No Known Activations