© 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. 10-GEMMASCOPE-RES-131K
    7. 19216
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or codes

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

    The neuron specifically detects the occurrence of the isotope label “32P.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ocide
    -2.42
     Mijn
    -2.42
    ↵↵
    -2.34
    actif
    -2.31
    事も
    -2.22
    kệ
    -2.22
     sufre
    -2.16
     caminhão
    -2.16
     attacco
    -2.13
     hilfre
    -2.08
    POSITIVE LOGITS
    I
    3.66
    m
    3.52
    ."
    3.08
    ).
    2.80
    。　　
    2.77
    ,"
    2.67
    。　
    2.63
    end
    2.56
    ):
    2.55
    be
    2.52
    Activations Density 0.030%

    No Known Activations