© 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. 22-GEMMASCOPE-RES-131K
    7. 72568
    Prev
    Next
    INDEX
    Explanations

    political rights and government

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

    This neuron is tracking how far into the document a token occurs (i.e. it activates in proportion to the token’s position).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     مباراة
    -1.79
     سينما
    -1.66
     acrescent
    -1.60
     mắn
    -1.57
     escrever
    -1.56
     fechar
    -1.54
     fotográfica
    -1.53
     ativar
    -1.52
     aceitar
    -1.48
    depuis
    -1.45
    POSITIVE LOGITS
     large
    1.58
     people
    1.53
    民众
    1.52
     political
    1.37
     for
    1.34
     law
    1.32
     formed
    1.31
     рисунок
    1.31
     no
    1.29
     напомина
    1.29
    Activations Density 0.028%

    No Known Activations