© 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. 113664
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

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

    the equals sign in function parameter assignments with default values.

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

    The neuron activates on numeric literal tokens (integer or floating‐point constants) 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
    шена
    -1.64
    他的
    -1.56
     wouldn
    -1.48
     couldn
    -1.45
     pendekatan
    -1.43
     would
    -1.41
    ется
    -1.38
    appara
    -1.32
    ciutto
    -1.29
     FRAMEWORK
    -1.29
    POSITIVE LOGITS
    こともあります
    1.52
    <bos>
    1.50
     jiné
    1.45
     adelant
    1.39
    狭い
    1.38
    ままで
    1.38
     autre
    1.38
     schnelle
    1.38
     otorg
    1.34
    Reducers
    1.33
    Activations Density 0.008%

    No Known Activations