© 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. 22-GEMMASCOPE-RES-131K
    7. 33079
    Prev
    Next
    INDEX
    Explanations

    verb + preposition

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

    This neuron detects methodological passive‐voice constructions reporting experimental procedures (e.g. “experiments were carried out in …”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    曖昧さ回避
    -0.96
    demment
    -0.96
    tuje
    -0.94
    ！！！！！
    -0.91
     maybe
    -0.91
    eador
    -0.91
    fizierung
    -0.89
    Ϋ
    -0.89
     satisfa
    -0.89
    北欧
    -0.88
    POSITIVE LOGITS
    ując
    0.95
     poucos
    0.93
     zwi
    0.90
    aked
    0.89
    assuming
    0.86
    clearly
    0.85
    Large
    0.85
    
    0.85
     kogo
    0.85
     deliciously
    0.85
    Activations Density 0.125%

    No Known Activations