© 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. 98429
    Prev
    Next
    INDEX
    Explanations

    problems, accidents, or restrictions

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

    The neuron is triggered by phrases where the author says their pictures aren’t currently uploaded or available.

    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
    kommer
    -1.23
     cualquier
    -1.20
    我们
    -1.16
    aları
    -1.11
     Gerais
    -1.10
    videoId
    -1.09
    scaleX
    -1.09
     DVDs
    -1.07
    Если
    -1.04
    UIControlState
    -1.04
    POSITIVE LOGITS
     it
    1.28
     yesterday
    1.11
     penjara
    1.04
     on
    1.00
     CONSE
    1.00
     ontem
    1.00
    もとも
    0.99
    stalgia
    0.96
     you
    0.96
     its
    0.96
    Activations Density 0.072%

    No Known Activations