© 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. 104425
    Prev
    Next
    INDEX
    Explanations

    programming code and configurations

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

    Java-related configuration files, code structures, and technical identifiers (especially classes, methods, and type declarations).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on CamelCase or PascalCase identifiers (e.g. class/type names) in code or XML tags.

    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
     fotografie
    -1.35
     cathédrale
    -1.31
    
    -1.24
    鹩
    -1.23
     dentelle
    -1.23
     анге
    -1.23
    Ꮠ
    -1.22
    "));
    -1.21
     pizarra
    -1.17
     abonnement
    -1.16
    POSITIVE LOGITS
     of
    1.70
     on
    1.47
    Mereka
    1.28
     at
    1.23
    imanapun
    1.20
     through
    1.19
     Seven
    1.18
     prazer
    1.17
     estos
    1.16
    aluno
    1.16
    Activations Density 0.011%

    No Known Activations