© 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. 117337
    Prev
    Next
    INDEX
    Explanations

    words starting with En

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

    The neuron consistently activates on tokens beginning with the letters “en” (e.g. encephalocranio, Ennio, ENU, Enceladus, enkephalin).

    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
     Schmerzen
    -0.95
     силы
    -0.88
     interesting
    -0.88
     поз
    -0.86
     ears
    -0.82
     bestimmten
    -0.81
     biệt
    -0.81
     твори
    -0.81
    制造
    -0.80
    felix
    -0.80
    POSITIVE LOGITS
     En
    1.85
     EN
    1.38
     Эн
    1.27
    En
    1.20
    ments
    1.18
    エン
    1.07
     エン
    1.05
    ment
    1.01
     enn
    0.96
    tieron
    0.91
    Activations Density 0.137%

    No Known Activations