© 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. 22-GEMMASCOPE-RES-131K
    7. 15001
    Prev
    Next
    INDEX
    Explanations

    `github.com` links and code comments

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

    The neuron activates on occurrences of the token “github,” i.e. when a GitHub URL or import path is referenced.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     when
    -1.65
     Only
    -1.55
     or
    -1.55
     With
    -1.52
     if
    -1.52
     after
    -1.41
     because
    -1.41
    Only
    -1.38
     For
    -1.38
     should
    -1.35
    POSITIVE LOGITS
    妧
    1.52
     EIGHT
    1.48
    regarding
    1.45
     NINE
    1.40
     inept
    1.39
    recently
    1.38
     unn
    1.37
    indicates
    1.31
     abd
    1.30
     insanely
    1.30
    Activations Density 0.000%

    No Known Activations