© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1399
    Prev
    Next
    INDEX
    Explanations

    enum, values, list attributes

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

    The neuron activates on unusually long, continuous tokens (e.g. multi‐character identifiers or numeric strings).

    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
    spaceBetween
    -0.89
     jaar
    -0.87
    ազմ
    -0.83
     ノ
    -0.79
     pasado
    -0.79
     Romagna
    -0.79
    werke
    -0.78
     hamb
    -0.78
    manned
    -0.78
     Mundial
    -0.77
    POSITIVE LOGITS
     value
    0.93
     values
    0.88
     VALUE
    0.75
     Value
    0.75
    value
    0.72
    enums
    0.70
    enumi
    0.70
    <td>
    0.70
    Conse
    0.70
     Ulysses
    0.69
    Activations Density 0.001%

    No Known Activations