© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77865
    Prev
    Next
    INDEX
    Explanations

    `setenv` commands, specific datasets, titles, research topics

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

    The neuron primarily detects numeric tokens (sequences of digits, such as years, version numbers, or other numbers).

    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
    migrationBuilder
    -0.79
     رسانه
    -0.74
     Е
    -0.74
     Hek
    -0.72
     Montserrat
    -0.70
     Rounded
    -0.69
     HasFactory
    -0.69
     Riks
    -0.68
     Superstar
    -0.67
     си
    -0.66
    POSITIVE LOGITS
    ucar
    0.88
    urangi
    0.76
     Asheville
    0.76
     matchups
    0.76
    dap
    0.75
     fabricantes
    0.75
     glider
    0.75
     holdings
    0.75
     CDM
    0.74
    лябин
    0.74
    Activations Density 0.022%

    No Known Activations