© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25157
    Prev
    Next
    INDEX
    Explanations

    specific terms and following words

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

    The main thing this neuron does is detect uppercase initialisms and acronyms (e.g. “ANN,” “PSG,” “EM,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     usados
    -0.97
     ocultar
    -0.94
     GONZ
    -0.93
     producciones
    -0.92
    ごと
    -0.91
    𝕣
    -0.91
    ecu
    -0.91
    blia
    -0.91
    gulier
    -0.90
     excluir
    -0.90
    POSITIVE LOGITS
    ⮕
    1.09
    ঋ
    1.02
     empfangen
    1.02
    东京
    1.00
     Gewebe
    1.00
    ßlich
    0.96
    сії
    0.96
    》.
    0.95
    めんな
    0.95
    ICHT
    0.95
    Activations Density 0.448%

    No Known Activations