© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58008
    Prev
    Next
    INDEX
    Explanations

    describing implementations or principles

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

    The neuron activates on the leading words of full‐sentence prose in code comments (e.g. “This,” “The,” “See”)—i.e. documentation sentences rather than code.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     “
    -1.69
    },
    -1.59
    )
    -1.52
    :
    -1.51
     =
    -1.49
    又
    -1.41
     a
    -1.39
     must
    -1.39
    tahui
    -1.38
     Wasch
    -1.38
    POSITIVE LOGITS
     mußten
    1.77
     ministère
    1.57
     Fungsi
    1.53
     dîner
    1.52
    probieren
    1.50
     ingenieros
    1.48
     cerdas
    1.46
     Bewußt
    1.45
     jeweiligen
    1.43
    indest
    1.42
    Activations Density 0.350%

    No Known Activations