© 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. 10-GEMMASCOPE-RES-131K
    7. 41790
    Prev
    Next
    INDEX
    Explanations

    function calls and definitions

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

    This neuron doesn’t respond to anything—it remains inactive (all-zero activations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    脔
    -3.67
    鸶
    -3.25
    xvii
    -3.17
    xiii
    -3.08
    ୌ
    -3.00
    鼍
    -2.98
    艄
    -2.98
    雠
    -2.91
     camiset
    -2.88
    BindingResult
    -2.88
    POSITIVE LOGITS
     or
    3.09
     in
    3.03
    2
    2.97
    1
    2.86
     
    2.86
     if
    2.83
     for
    2.83
     at
    2.70
     when
    2.70
     as
    2.69
    Activations Density 0.737%

    No Known Activations