© 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. 80778
    Prev
    Next
    INDEX
    Explanations

    camera system usage

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

    The main thing this neuron does is detect occurrences of the word “camera” (in any capitalization or script).

    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
    "
    -1.85
    也
    -1.80
    ]
    -1.73
    '
    -1.66
    </h5>
    -1.65
     was
    -1.65
     similarly
    -1.60
    ,"
    -1.60
     of
    -1.59
    叠
    -1.56
    POSITIVE LOGITS
     tomando
    2.05
     siguiendo
    1.80
     смогли
    1.79
    渽
    1.78
     realizando
    1.78
     poniendo
    1.71
     buscando
    1.68
    
    1.63
    もありますが
    1.59
    沩
    1.59
    Activations Density 0.027%

    No Known Activations