© 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. 10-GEMMASCOPE-RES-131K
    7. 70810
    Prev
    Next
    INDEX
    Explanations

    camera view and image capture

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

    The neuron activates specifically whenever the token “camera” appears.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     was
    -2.89
    (
    -2.78
    但我
    -2.64
     Which
    -2.59
     similarly
    -2.52
     they
    -2.50
    "
    -2.48
     palav
    -2.47
    綃
    -2.44
    
    -2.44
    POSITIVE LOGITS
    .
    3.77
    渽
    3.19
     realizando
    2.89
     buscando
    2.78
     tratando
    2.64
     utilisées
    2.56
     generar
    2.36
     tornar
    2.34
    覬
    2.33
    Ꮸ
    2.31
    Activations Density 0.009%

    No Known Activations