© 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. 90843
    Prev
    Next
    INDEX
    Explanations

    quantities of millions of people

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

    This neuron is essentially inactive—it never consistently fires and does not detect any meaningful pattern.

    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
     on
    -1.33
     становника
    -1.16
     what
    -1.10
     big
    -1.10
     From
    -1.08
     or
    -1.07
     While
    -1.06
     in
    -1.06
     until
    -1.04
    siamo
    -1.02
    POSITIVE LOGITS
     tens
    1.51
     millions
    1.48
     thousands
    1.46
    tens
    1.25
    Tens
    1.14
    potentially
    1.10
    (,
    1.10
    zten
    1.09
     overal
    1.08
     Tens
    1.07
    Activations Density 0.060%

    No Known Activations