© 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. 58542
    Prev
    Next
    INDEX
    Explanations

    photo gallery

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

    This neuron detects explicit references to viewing or accessing embedded media (e.g. “see the video,” “view photo,” “picture here”).

    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
    eneral
    -0.85
    figer
    -0.72
    jol
    -0.67
    snapshot
    -0.67
     falsi
    -0.66
    깅
    -0.66
    eaux
    -0.65
     заболе
    -0.65
     волос
    -0.64
     LOS
    -0.64
    POSITIVE LOGITS
     gallery
    6.44
     Gallery
    5.13
    gallery
    5.06
    Gallery
    4.81
     galleries
    4.69
     GALLERY
    4.19
    GALLERY
    3.67
     Galleries
    3.44
     galerie
    3.30
     гале
    3.23
    Activations Density 0.101%

    No Known Activations