© 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. 34-GEMMASCOPE-RES-131K
    7. 73532
    Prev
    Next
    INDEX
    Explanations

    key : followed by value

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

    The neuron fires on standalone numeric tokens (e.g. multi‐digit identifiers or codes).

    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
    uges
    -0.89
     løpet
    -0.81
     estimated
    -0.78
     estimates
    -0.75
    set
    -0.75
    UEGO
    -0.75
    atians
    -0.75
     estimate
    -0.74
    estimate
    -0.74
     agreed
    -0.73
    POSITIVE LOGITS
    läs
    0.93
     sobot
    0.91
     Wednesday
    0.86
     pozn
    0.85
     newspapers
    0.83
     län
    0.82
     HERE
    0.82
    Espresso
    0.81
     espresso
    0.81
     \|
    0.80
    Activations Density 0.002%

    No Known Activations