© 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. 112556
    Prev
    Next
    INDEX
    Explanations

    programming code, Linq queries

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

    the keyword "this" in programming code, particularly in object-oriented contexts like method parameters, extension methods, and member access.

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

    The neuron fires strongly on programming-language import statements (i.e., “import X…” lines).

    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
     tiež
    -1.43
    PushMatrix
    -1.31
    ≦
    -1.30
    Leftrightarrow
    -1.25
     tiring
    -1.21
     lipca
    -1.16
     tener
    -1.13
    isering
    -1.12
    OrBuilder
    -1.12
    uoti
    -1.11
    POSITIVE LOGITS
    ↵
    1.40
     others
    1.21
    paku
    1.13
    ͖
    1.09
    jointe
    1.05
     they
    1.03
    empre
    1.02
    ICTO
    1.02
    Mixture
    1.02
    Produtos
    1.02
    Activations Density 0.043%

    No Known Activations