© 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. 64244
    Prev
    Next
    INDEX
    Explanations

    legal documents and technical discussions

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

    This neuron fires on markers of passive‐voice constructions (e.g. auxiliary verbs like “werden,” “tika” plus past participles) across languages.

    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
     has
    -1.21
     didn
    -1.20
     grew
    -1.15
     hadn
    -1.10
     Took
    -1.09
     didnt
    -1.06
    didn
    -1.00
    lında
    -0.98
     couldn
    -0.97
     hast
    -0.95
    POSITIVE LOGITS
     taken
    1.73
     shown
    1.52
     done
    1.47
     করা
    1.41
     undertaken
    1.40
     explored
    1.33
     discussed
    1.30
     eaten
    1.27
     introduced
    1.24
     evaluated
    1.21
    Activations Density 0.007%

    No Known Activations