© 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. 72126
    Prev
    Next
    INDEX
    Explanations

    string variable declarations and assignments

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

    The neuron fires most strongly on Java type tokens and related literals (e.g. “String”, “int”, “boolean”, null, and string‐literal quotes).

    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
     podido
    -1.35
     obtuvo
    -1.30
    brainly
    -1.25
     prodotti
    -1.23
     การ
    -1.23
    鐃
    -1.21
    different
    -1.20
     compró
    -1.19
     다른
    -1.18
     trabalha
    -1.18
    POSITIVE LOGITS
     if
    1.61
     for
    1.54
    </strong>
    1.44
    </h2>
    1.20
     of
    1.14
    niczka
    1.09
     deserve
    1.09
    </sup>
    1.08
    TCHAR
    1.05
     whence
    1.04
    Activations Density 0.037%

    No Known Activations