© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59074
    Prev
    Next
    INDEX
    Explanations

    multi-threaded code and files

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

    The neuron responds strongly to non-Latin (e.g. CJK) character tokens.

    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
     JsonResponse
    -0.83
     prompted
    -0.81
     of
    -0.79
     as
    -0.79
     regarding
    -0.76
     stöd
    -0.74
     encephal
    -0.72
    iak
    -0.71
     Requested
    -0.70
     where
    -0.70
    POSITIVE LOGITS
     Leopard
    1.02
    夏天
    0.90
    actually
    0.87
    ковым
    0.85
    kembang
    0.85
     aussit
    0.84
     Worte
    0.83
     malheureux
    0.82
    retudo
    0.82
     gewe
    0.82
    Activations Density 0.001%

    No Known Activations