© 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. 34-GEMMASCOPE-RES-131K
    7. 92854
    Prev
    Next
    INDEX
    Explanations

    German words

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

    The neuron fires on string-literal tokens that look like file or module path names in import/include/require directives.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ようで
    -0.82
     vacas
    -0.78
    tomatik
    -0.77
    后再
    -0.75
    رت
    -0.75
     повіт
    -0.74
     ū
    -0.74
     вси
    -0.73
     h
    -0.73
     сообщает
    -0.72
    POSITIVE LOGITS
    ⒐
    1.07
     Bewußt
    1.02
     COMPLE
    0.95
     INCLUDING
    0.93
     Momente
    0.93
     termé
    0.92
     NUMBER
    0.91
    aimeJ
    0.91
     MIGHT
    0.90
     SUCH
    0.90
    Activations Density 0.072%

    No Known Activations