© 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. 69347
    Prev
    Next
    INDEX
    Explanations

    Python module setup

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

    The neuron selectively fires on square‐bracket tokens that open array or list literals (e.g. the “\[” starting styleUrls, plugins, dependencies, srcs, rules, etc.).

    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
     berätt
    -1.42
    醞
    -1.40
    違った
    -1.31
     trouxe
    -1.28
     fazia
    -1.26
     hiasan
    -1.23
    。<
    -1.22
    árias
    -1.20
     附
    -1.20
     tandis
    -1.18
    POSITIVE LOGITS
     and
    2.45
     at
    1.31
    素晴らしい
    1.30
     including
    1.29
    wolle
    1.28
     a
    1.27
     ۱۴۰۰
    1.27
    fikasi
    1.26
     okol
    1.25
     such
    1.24
    Activations Density 0.010%

    No Known Activations