© 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. 34913
    Prev
    Next
    INDEX
    Explanations

    groups and plotting

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

    The neuron flags mentions of specific array‐ or dataset‐type classes (e.g. NumPy arrays, XArray DataArray or Dataset).

    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
     FRANCIS
    -0.71
     حاصل
    -0.69
     Gedanken
    -0.69
     retira
    -0.69
     Joy
    -0.69
    த்த
    -0.69
     seines
    -0.68
    цент
    -0.67
     на
    -0.66
     Pam
    -0.65
    POSITIVE LOGITS
     subgroups
    1.09
     Groups
    1.00
     groups
    1.00
    createTable
    0.96
     group
    0.95
    Groups
    0.95
    attrs
    0.93
    Group
    0.87
     Grup
    0.87
    Группа
    0.86
    Activations Density 0.005%

    No Known Activations