© 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. 38568
    Prev
    Next
    INDEX
    Explanations

    list-related programming constructs

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

    The neuron strongly activates on the substring “lst” (e.g. in variable names or IDs), i.e. it’s detecting that “lst” token.

    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
    </td>
    -2.80
    0
    -2.69
    敺
    -2.61
    闿
    -2.56
    
    -2.56
     "")
    -2.55
    屜
    -2.55
    ”.
    -2.53
    )");
    -2.50
    flasche
    -2.45
    POSITIVE LOGITS
    I
    3.66
    ta
    2.89
     стал
    2.70
     '
    2.67
    小伙伴
    2.47
    很好的
    2.44
     involucrados
    2.42
    enablog
    2.39
    ll
    2.38
    にの
    2.36
    Activations Density 0.001%

    No Known Activations