© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6846
    Prev
    Next
    INDEX
    Explanations

    flickr and technical platforms

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

    The neuron fires on mentions of “Flickr,” i.e. references to the Flickr image‐hosting service.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    呖
    -3.16
    伃
    -2.78
    辚
    -2.77
    hasMoreElements
    -2.77
     éditoriale
    -2.59
     enfance
    -2.52
    潆
    -2.52
    ⸂
    -2.44
     et
    -2.44
     術
    -2.42
    POSITIVE LOGITS
     
    3.58
    .
    3.47
     '
    2.84
    '
    2.67
     ...
    2.55
    啬
    2.42
    ふた
    2.25
    変わった
    2.17
    蚡
    2.14
     Our
    2.13
    Activations Density 0.001%

    No Known Activations