© 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. 102757
    Prev
    Next
    INDEX
    Explanations

    class names after imports

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

    the opening triple-quote of Python docstrings.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on the Python triple‐quote characters (""" or ''') that mark the start or end of docstrings.

    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
     Einladung
    -1.73
     Eigentü
    -1.69
     them
    -1.63
                
    -1.63
     Personally
    -1.59
     Year
    -1.57
    
    -1.55
     była
    -1.52
     zahlreichen
    -1.52
     Huge
    -1.48
    POSITIVE LOGITS
    鏵
    1.59
     diego
    1.51
     titel
    1.38
    TestTools
    1.38
     Salto
    1.35
    gradable
    1.35
    “
    1.35
     bourg
    1.34
    鳢
    1.34
     barrio
    1.34
    Activations Density 0.002%

    No Known Activations