© 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. 81423
    Prev
    Next
    INDEX
    Explanations

    public code declarations

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

    The neuron is keyed to recognize HTTP method annotations—especially the “POST” token—in Spring MVC controller definitions.

    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
     their
    -0.82
     additional
    -0.81
    ')):
    -0.81
     even
    -0.80
    Lastly
    -0.80
    jene
    -0.79
     from
    -0.79
     those
    -0.78
    stub
    -0.78
     at
    -0.78
    POSITIVE LOGITS
    public
    1.05
     Surv
    1.00
    annas
    0.96
     response
    0.90
     SIC
    0.85
     productie
    0.82
     zweier
    0.81
     мимо
    0.81
    ៀ
    0.80
     entrant
    0.79
    Activations Density 0.002%

    No Known Activations