© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100246
    Prev
    Next
    INDEX
    Explanations

    SQL and code data types

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

    whitespace or formatting tokens in structured data like code, tables, or configuration files.

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

    The neuron activates on numeric literal tokens (plain numbers) in code or data contexts.

    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
    睒
    -1.35
     inoltre
    -1.27
     atriz
    -1.15
    Qualifications
    -1.12
    compañ
    -1.10
     profissionais
    -1.10
     serão
    -1.09
     gebruik
    -1.09
     however
    -1.09
    dits
    -1.09
    POSITIVE LOGITS
     what
    1.42
     selera
    1.27
     its
    1.27
    كاتب
    1.25
    there
    1.25
     another
    1.23
    aiuto
    1.23
     TWO
    1.19
     some
    1.17
     pengaruh
    1.16
    Activations Density 0.089%

    No Known Activations