© 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. 22-GEMMASCOPE-RES-131K
    7. 39082
    Prev
    Next
    INDEX
    Explanations

    court, rats, metals, urine, periods

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

    scientific or technical content in academic papers or code files.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on numeric tokens, i.e. numbers and numeric values in the 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_22/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
    ?
    -1.03
    B
    -0.90
     trước
    -0.88
    Â
    -0.86
     Will
    -0.84
    !
    -0.84
    U
    -0.83
    预
    -0.82
    Curi
    -0.81
     listos
    -0.81
    POSITIVE LOGITS
     bendera
    1.06
     chaleco
    1.06
     helicóptero
    1.02
    Makanan
    1.00
    などの
    1.00
     både
    1.00
    Sied
    0.98
     both
    0.97
     kekasih
    0.97
     різних
    0.97
    Activations Density 0.057%

    No Known Activations