© 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. 34-GEMMASCOPE-RES-131K
    7. 3175
    Prev
    Next
    INDEX
    Explanations

    leader titles

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

    The neuron is a “content‐word” detector that fires most strongly on nouns—especially proper nouns, titles, and other key topic words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     jurado
    -1.04
     beneficiario
    -0.99
     ministerio
    -0.95
     patente
    -0.91
     PATIENT
    -0.91
     Pemerintah
    -0.90
     Ministério
    -0.90
     Senado
    -0.88
     decreto
    -0.86
     discí
    -0.85
    POSITIVE LOGITS
     CEO
    4.47
     Director
    4.31
     director
    4.28
     chairman
    3.98
     Chief
    3.78
     Chairman
    3.75
     president
    3.58
     manager
    3.38
     chief
    3.38
    Director
    3.28
    Activations Density 0.322%

    No Known Activations