© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91789
    Prev
    Next
    INDEX
    Explanations

    disclosures including functionality

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

    The neuron flags non-Latin (CJK) characters—i.e. Chinese text.

    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
     however
    -1.05
    However
    -1.01
    bánh
    -0.95
     surprises
    -0.88
     azonban
    -0.85
    rilla
    -0.84
    entikan
    -0.84
     imidlertid
    -0.83
    zám
    -0.83
    gül
    -0.83
    POSITIVE LOGITS
    而
    5.22
     mà
    4.34
     while
    3.56
     而
    3.02
     mentre
    2.72
     mientras
    2.45
    while
    2.44
    ⽽
    2.23
    而在
    2.20
     enquanto
    2.03
    Activations Density 0.006%

    No Known Activations