© 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. 33545
    Prev
    Next
    INDEX
    Explanations

    object string representation

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

    This neuron detects function or method definitions in source code, especially special or “dunder” methods like __str__, __unicode__, and similar toString-style 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_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
    opie
    -1.38
     报告
    -1.23
    inerary
    -1.23
    '\\
    -1.22
    '
    -1.21
     电脑
    -1.18
    arrived
    -1.17
    received
    -1.16
     actionTypes
    -1.14
    accepted
    -1.13
    POSITIVE LOGITS
    It
    1.13
      
    1.09
     name
    1.07
     classy
    1.05
     noteworthy
    1.03
     prominent
    1.02
    B
    1.01
     one
    0.98
     tangible
    0.97
     first
    0.96
    Activations Density 0.001%

    No Known Activations