© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 87319
    Prev
    Next
    INDEX
    Explanations

    linked list, table cell, oligonucleotide

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

    references to data structures like LinkedList and TableCell.

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

    The neuron fires on capitalized identifiers and type names (e.g. class or data‐structure names) in code.

    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
    â
    -2.58
    In
    -2.31
     .
    -2.27
    𓐍
    -2.27
    AL
    -2.23
    *
    -2.22
    Some
    -2.20
    1
    -2.16
    Many
    -2.14
    Approximately
    -2.13
    POSITIVE LOGITS
    chuckles
    2.31
     examinar
    2.30
     habilitar
    2.27
    genodigd
    2.20
     transmitir
    2.19
     personalizar
    2.13
    黻
    2.11
     betekent
    2.09
    
    2.05
    viembre
    1.99
    Activations Density 0.001%

    No Known Activations