© 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. 34-GEMMASCOPE-RES-131K
    4. 23800
    Prev
    Next
    INDEX
    Explanations

    copyright notices and software code

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

    The neuron strongly activates on sequences containing an at-sign (’@’), i.e. fragments of email addresses.

    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
     MEETING
    -0.75
     contained
    -0.73
     resolve
    -0.71
    esch
    -0.69
    (['/
    -0.68
    ఖ
    -0.66
     vezes
    -0.66
    featured
    -0.66
     cryst
    -0.65
    ình
    -0.64
    POSITIVE LOGITS
    onload
    0.79
    nically
    0.77
    XMLSchema
    0.74
    SESSION
    0.74
    릴
    0.71
    Summar
    0.67
    mbert
    0.67
    Alles
    0.66
    homework
    0.66
     ItemStack
    0.66
    Activations Density 0.057%

    No Known Activations