© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20306
    Prev
    Next
    INDEX
    Explanations

    like me, or unlike me

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

    The neuron is primarily triggered by mentions of the Republican side in a political comparison—e.g. references to “Republicans,” “Bush,” or other GOP actors.

    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
     nettement
    -1.34
     zapato
    -1.30
     trente
    -1.25
     bolsillo
    -1.23
     tellement
    -1.22
     artwork
    -1.22
    homonymie
    -1.20
    咚
    -1.17
     agujero
    -1.16
     decirle
    -1.14
    POSITIVE LOGITS
    when
    1.38
     which
    1.37
    روب
    1.33
     who
    1.33
     to
    1.22
     ultimi
    1.19
    ]}
    1.19
     keď
    1.17
    (/^
    1.13
    whose
    1.09
    Activations Density 0.038%

    No Known Activations