© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34020
    Prev
    Next
    INDEX
    Explanations

    Lin Po, Skin Cancer

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

    JavaScript import statements with curly braces.

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

    The neuron fires specifically on the named‐import braces and the identifiers inside them—i.e. tokens that appear in “import { … } from …” statements.

    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
     décès
    -1.41
    tså
    -1.38
    Leírás
    -1.37
    involved
    -1.34
     Terima
    -1.27
     Fácil
    -1.26
     galeri
    -1.26
    Также
    -1.22
     blusa
    -1.21
    <bos>
    -1.20
    POSITIVE LOGITS
    They
    1.34
    1.34
     (
    1.30
     v
    1.27
     M
    1.26
     of
    1.25
     O
    1.23
     T
    1.23
     But
    1.23
    したが
    1.22
    Activations Density 0.003%

    No Known Activations