© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63163
    Prev
    Next
    INDEX
    Explanations

    commit and apply changes

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

    The neuron fires on the “dot” operator and surrounding tokens in fluent-style method call chains (e.g. identifier . method()).

    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
    cores
    -0.79
    takers
    -0.74
     volte
    -0.74
     fint
    -0.73
     servis
    -0.72
    usstsein
    -0.71
     Held
    -0.70
     mysqli
    -0.69
    KF
    -0.69
    otto
    -0.68
    POSITIVE LOGITS
    commit
    1.25
     commit
    1.14
     put
    1.08
    ਖ਼
    0.98
    apply
    0.97
    Commit
    0.97
    putString
    0.95
     editor
    0.94
     apply
    0.91
     committing
    0.90
    Activations Density 0.001%

    No Known Activations