© 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. 22-GEMMASCOPE-RES-131K
    4. 128431
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on the “public” keyword in code, flagging public declarations (e.g. methods or constructors).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    public class/function

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ureusement
    -1.22
    atisfaction
    -1.09
    mindedness
    -1.06
    mme
    -1.04
    atization
    -1.02
    鬟
    -1.02
    ateness
    -1.02
     aí
    -1.00
    greja
    -0.98
    ihnachten
    -0.98
    POSITIVE LOGITS
     only
    0.91
     stesse
    0.88
     currently
    0.84
     need
    0.84
    를
    0.83
    āb
    0.82
     torte
    0.82
    摳
    0.81
     baguette
    0.80
     الاجتماعي
    0.79
    Activations Density 0.003%

    No Known Activations