© 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. 128150
    Prev
    Next
    INDEX
    Explanations

    countries, nations, communities

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

    The neuron activates on occurrences of the word “this” when it introduces a specific entity (e.g. “this nation,” “this country,” “this town”).

    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
     such
    -1.30
     also
    -1.29
     the
    -1.27
     themselves
    -1.23
    是什么意思
    -1.16
     would
    -1.16
    还真
    -1.13
     some
    -1.09
     avrebbe
    -1.08
    きち
    -1.08
    POSITIVE LOGITS
    StoryboardSegue
    1.47
    )//
    1.38
    orianCalendar
    1.35
     что
    1.34
    merate
    1.31
    理石
    1.31
     silueta
    1.30
    ]
    1.30
    ！”
    1.28
     dataGridView
    1.27
    Activations Density 0.018%

    No Known Activations