© 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. 106796
    Prev
    Next
    INDEX
    Explanations

    political discourse and foreign terms

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

    The neuron is strongly activated by capitalized words (i.e. proper names and other uppercase-initial tokens).

    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
    området
    -1.09
     "...
    -1.08
     económicas
    -1.06
    akujem
    -1.05
     overall
    -1.05
    Exciting
    -1.02
    richting
    -1.02
     grote
    -1.00
    lauren
    -1.00
     autén
    -0.99
    POSITIVE LOGITS
     combustible
    1.06
    又
    0.98
     дета
    0.97
     Silicon
    0.95
     rema
    0.94
     POLIT
    0.93
    కు
    0.91
    calculus
    0.91
    ustomed
    0.91
    もし
    0.91
    Activations Density 0.140%

    No Known Activations