© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 120060
    Prev
    Next
    INDEX
    Explanations

    EDT, Hg, pyp, glog

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

    the chemical symbol "Hg" (mercury) or fragments of "Google" in technical and scientific texts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on any token containing the letter sequence “og” (e.g. in “Google,” “Skook,” or the chemical symbol “Hg”).

    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
     帅气
    -2.59
     neuen
    -2.56
    ↵
    -2.50
     llamó
    -2.33
    皛
    -2.31
     BUT
    -2.20
     aprecia
    -2.20
     ибо
    -2.19
     Antrags
    -2.17
     Erwä
    -2.17
    POSITIVE LOGITS
    4
    2.97
    {
    2.88
    ]
    2.66
    or
    2.61
    9
    2.56
    ’
    2.56
    7
    2.55
    2
    2.53
    in
    2.41
    –
    2.34
    Activations Density 0.003%

    No Known Activations