© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109039
    Prev
    Next
    INDEX
    Explanations

    image file paths

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

    The neuron fires on tokens that are parts of image file paths or names (e.g. pieces of URLs/paths pointing to logos, slides, .png/.svg files).

    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
     which
    -1.18
     or
    -1.02
     and
    -0.97
     peculiarities
    -0.90
     for
    -0.88
    xos
    -0.88
     his
    -0.88
     By
    -0.88
    })$,
    -0.88
     Jahren
    -0.87
    POSITIVE LOGITS
     icon
    1.33
     icono
    1.26
     durer
    1.22
    png
    1.21
     occuper
    1.16
     logo
    1.13
     verkligen
    1.11
     redus
    1.05
    resized
    1.05
     icons
    1.03
    Activations Density 0.025%

    No Known Activations