© 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. 2866
    Prev
    Next
    INDEX
    Explanations

    head of

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

    The neuron flags words that denote leadership or top-level positions (e.g. “head,” “chief,” “central,” “primary”).

    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
     creando
    -0.94
     speziellen
    -0.88
    可能是
    -0.87
     chegando
    -0.86
     jednou
    -0.85
     geliefert
    -0.85
     ansehen
    -0.85
     mejorando
    -0.81
    بدو
    -0.81
    开头
    -0.80
    POSITIVE LOGITS
     of
    1.95
     hon
    1.16
     guy
    1.08
     ofthe
    1.05
     strateg
    0.98
     thereof
    0.96
    =")
    0.93
    Poznám
    0.93
     hierdie
    0.91
     surgical
    0.91
    Activations Density 0.033%

    No Known Activations