© 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. 10-GEMMASCOPE-RES-131K
    4. 22060
    Prev
    Next
    INDEX
    Explanations

    this. or self

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

    The neuron detects object‐context references in code, i.e. occurrences of “this” or “self” (often followed by a dot or underscore) indicating property or method access.

    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
     of
    -1.67
     
    -1.59
     According
    -1.42
    中秋
    -1.39
     Those
    -1.39
     ПОД
    -1.38
    先日
    -1.38
    3
    -1.35
    1
    -1.34
    2
    -1.33
    POSITIVE LOGITS
     a
    2.42
    </h2>
    1.74
     not
    1.64
    </h4>
    1.61
     about
    1.56
     something
    1.56
    YECTO
    1.53
    </b>
    1.52
    yship
    1.52
    layed
    1.51
    Activations Density 0.004%

    No Known Activations