© 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. 77377
    Prev
    Next
    INDEX
    Explanations

    World Bank, Ruger, Tower Hamlets, pilot

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

    The neuron fires on very short alphanumeric tokens—especially two‐letter or code‐like fragments (e.g. “id” or “gr”) that typically appear as identifiers or currency/country 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
     and
    -1.35
     after
    -0.95
     from
    -0.92
     before
    -0.91
     MUNICIPAL
    -0.91
     with
    -0.90
     began
    -0.90
     for
    -0.89
     церемо
    -0.88
     Wednesday
    -0.86
    POSITIVE LOGITS
    гән
    1.08
     віта
    1.05
     sırt
    1.04
     spectacular
    1.00
     soooo
    0.99
     oes
    0.99
     Pooja
    0.98
     calore
    0.98
    Thankfully
    0.98
     ktoś
    0.98
    Activations Density 0.000%

    No Known Activations