© 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. 22-GEMMASCOPE-RES-131K
    7. 129366
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on the transitional/ordinal words that introduce or describe image/figure captions (e.g. “First,” “And now,” “two,” “images,” “show,” “where”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    view with images or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Pristup
    -1.24
     consid
    -1.10
    indicate
    -1.09
     commencer
    -1.08
    began
    -1.04
    renti
    -1.03
    begins
    -1.01
    上涨
    -1.00
    introdu
    -0.99
    considered
    -0.98
    POSITIVE LOGITS
     detailed
    1.41
     showing
    1.41
     full
    1.27
     details
    1.17
     actually
    1.16
     additional
    1.16
     view
    1.12
     of
    1.10
     with
    1.08
     after
    1.04
    Activations Density 0.024%

    No Known Activations