© 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. 10-GEMMASCOPE-RES-131K
    7. 9811
    Prev
    Next
    INDEX
    Explanations

    places and specific entities

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

    The neuron fires on mentions of country or territory names—especially small island nations.

    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
    廔
    -3.22
    觧
    -3.08
    ଝ
    -3.06
    Ꝑ
    -3.06
    靫
    -2.98
    甞
    -2.89
    渽
    -2.89
    蛧
    -2.88
    geſ
    -2.83
    gucig
    -2.81
    POSITIVE LOGITS
     I
    2.52
     i
    2.36
    This
    2.31
    ".
    2.25
     
    2.22
     ”
    2.20
    {
    2.16
    for
    2.13
    as
    2.13
              
    2.13
    Activations Density 0.001%

    No Known Activations