© 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. 34-GEMMASCOPE-RES-131K
    7. 26025
    Prev
    Next
    INDEX
    Explanations

    mutual consent

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

    The neuron consistently lights up on code binding constructs—things like let-bindings, destructuring braces, match patterns, “in,” and related symbol tokens (e.g. “=”, “&”, “&&”) used to bind or assign variables.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     ympä
    -0.84
    したので
    -0.84
     noiva
    -0.79
     péld
    -0.79
    antwoorde
    -0.73
    ଉ
    -0.73
     Means
    -0.72
    oward
    -0.72
    tiska
    -0.71
    Jura
    -0.71
    POSITIVE LOGITS
     mut
    4.34
    mut
    3.84
     mutual
    2.59
     Mut
    2.42
    Mut
    2.34
     mutually
    2.33
    MUT
    2.16
     mutu
    1.96
     MUT
    1.91
    mutual
    1.90
    Activations Density 0.015%

    No Known Activations