© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41266
    Prev
    Next
    INDEX
    Explanations

    image file paths

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

    This neuron detects occurrences of “images” in file‐path or URL references (i.e. the “images/” directory token).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     který
    -1.50
    してます
    -1.48
     considered
    -1.48
     described
    -1.45
     if
    -1.43
     termed
    -1.41
    يارات
    -1.38
     natomiast
    -1.38
    面接
    -1.37
     regarded
    -1.35
    POSITIVE LOGITS
    ㈬
    1.68
    er
    1.56
     bensin
    1.54
     bese
    1.51
     perna
    1.47
    ㈰
    1.47
     vorder
    1.45
     myster
    1.45
     diffic
    1.44
     of
    1.43
    Activations Density 0.003%

    No Known Activations