© 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. 110877
    Prev
    Next
    INDEX
    Explanations

    search christian lyrics

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

    The neuron strongly activates on numeric tokens and figures (e.g. years, quantities, measurements) 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_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
    fortun
    -0.87
    riga
    -0.81
     Gewebe
    -0.78
     DISABLE
    -0.78
    etka
    -0.75
    ymi
    -0.75
    dolu
    -0.74
    Contrary
    -0.73
     ontstaan
    -0.73
    áles
    -0.73
    POSITIVE LOGITS
    Feature
    0.90
     feature
    0.90
     Feature
    0.82
     stock
    0.81
    FEATURE
    0.79
    izhou
    0.79
     ballroom
    0.79
     diy
    0.79
     environmental
    0.78
     DIY
    0.77
    Activations Density 0.003%

    No Known Activations