© 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. 43979
    Prev
    Next
    INDEX
    Explanations

    italian people and places

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

    This neuron responds to mentions of elections and related political bodies or events (e.g. “Senate election,” “European Parliament election”) often coupled with dates or regions.

    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
     like
    -1.12
    ff
    -1.11
     просто
    -1.09
     See
    -1.09
     Say
    -1.05
     simplemente
    -1.05
     einfach
    -1.02
    ;
    -1.02
     see
    -1.02
     naše
    -1.00
    POSITIVE LOGITS
     jurídico
    1.36
     hva
    1.31
     experimento
    1.22
     eksper
    1.20
     trabalhadores
    1.17
     eenige
    1.16
     préstamo
    1.16
    ȼ
    1.16
     eenig
    1.16
     organizador
    1.16
    Activations Density 0.315%

    No Known Activations