© 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. 22-GEMMASCOPE-RES-131K
    7. 436
    Prev
    Next
    INDEX
    Explanations

    posted photos and images

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

    This neuron detects references to posted or published media—words like photo(s), image(s), screenshot(s), page, released, posted, on-line, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    sodik
    -1.32
    みたいな
    -1.14
    aktur
    -1.08
     қ
    -1.06
    覗
    -1.05
    NewValue
    -1.03
     відчу
    -1.02
    拦
    -1.02
    ikaze
    -1.02
    のような
    -1.02
    POSITIVE LOGITS
     images
    1.77
     photos
    1.55
     pictures
    1.41
     image
    1.39
     photo
    1.29
     photographs
    1.28
    一张
    1.19
    一張
    1.11
     of
    1.08
     درد
    1.02
    Activations Density 0.075%

    No Known Activations