© 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. 14783
    Prev
    Next
    INDEX
    Explanations

    programming entities and identifiers

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

    The neuron fires on module/package path segments (e.g. the identifiers in import or package declarations).

    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
     that
    -1.94
     it
    -1.79
     this
    -1.70
     for
    -1.66
     change
    -1.48
     seemingly
    -1.46
     kini
    -1.41
     until
    -1.40
     varying
    -1.38
    áty
    -1.38
    POSITIVE LOGITS
    tifies
    1.66
     dekol
    1.38
     rése
    1.38
    了一眼
    1.32
     besonder
    1.31
     pewno
    1.31
     kabát
    1.30
     stratég
    1.29
    értel
    1.28
     lemari
    1.25
    Activations Density 0.035%

    No Known Activations