© 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. 30344
    Prev
    Next
    INDEX
    Explanations

    how it happens

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

    The neuron flags tokens from foreign‐language passages (non-English words and scripts).

    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
    かどうか
    -1.21
     吗
    -1.00
    吗
    -0.99
    嗎
    -0.98
     either
    -0.96
     like
    -0.92
     irgendwo
    -0.90
     needn
    -0.89
     nämlich
    -0.87
     irgendwann
    -0.84
    POSITIVE LOGITS
     eigentlich
    1.84
     denn
    1.77
     vlast
    1.41
     egentligen
    1.25
    บ้าง
    1.22
     wohl
    1.19
     eigenlijk
    1.16
     egentlig
    1.15
     соб
    1.12
    呀
    1.12
    Activations Density 0.009%

    No Known Activations