© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128487
    Prev
    Next
    INDEX
    Explanations

    code execution context

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

    This neuron fires on object-method calls (i.e. tokens involved in “object.method(…)” chaining in code).

    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
     correctes
    -2.02
    鳚
    -1.93
     Milán
    -1.83
     utiles
    -1.80
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.77
     gratuites
    -1.76
     sonda
    -1.70
     plafon
    -1.70
    Veuillez
    -1.70
     fiables
    -1.70
    POSITIVE LOGITS
     same
    2.11
      
    1.67
    showed
    1.63
     
    1.58
     and
    1.54
    le
    1.54
     but
    1.54
     “
    1.54
    occurs
    1.48
    <bos>
    1.45
    Activations Density 0.042%

    No Known Activations