© 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. 63048
    Prev
    Next
    INDEX
    Explanations

    government institutions and regulations

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

    The neuron consistently lights up on longer, multi‐syllable content words (i.e. words above a certain length).

    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
     biodiesel
    -1.11
     marginalized
    -1.03
    אָ
    -0.99
     genomics
    -0.99
     nanoparticle
    -0.96
     Robust
    -0.96
    為何
    -0.96
     Globalization
    -0.96
     webcam
    -0.94
    ācija
    -0.94
    POSITIVE LOGITS
     manpower
    1.05
     ибо
    1.02
     federal
    1.02
     Manpower
    0.94
     intensa
    0.93
    Federal
    0.93
     basically
    0.92
     Federal
    0.91
    Soviet
    0.91
    ьет
    0.88
    Activations Density 0.133%

    No Known Activations