© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116974
    Prev
    Next
    INDEX
    Explanations

    visual media followed by of

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

    The neuron detects mentions of visual media—words referring to photos, pictures, selfies, videos, or posted images.

    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
     Menschheit
    -1.56
     acoged
    -1.37
     ahorrar
    -1.32
     aisladas
    -1.30
     herida
    -1.26
     Schwangerschaft
    -1.21
     lakukan
    -1.17
     dureza
    -1.17
     aislada
    -1.16
     emisiones
    -1.16
    POSITIVE LOGITS
     of
    9.81
    ของ
    3.42
     của
    2.61
     של
    2.55
    of
    2.25
     from
    1.55
     Of
    1.54
    ของคุณ
    1.52
    もちろん
    1.52
     των
    1.47
    Activations Density 0.078%

    No Known Activations