© 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. 10349
    Prev
    Next
    INDEX
    Explanations

    camera lens mount

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

    The neuron detects occurrences of photographic lens mount names or specifications (e.g. “Pentacon-Six mount,” Tamron lens mount, Canon EF mount).

    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
    」、「
    -1.64
    瑧
    -1.64
     on
    -1.59
    ograf
    -1.48
     ligne
    -1.45
    
    -1.38
    "">
    -1.34
    ="+
    -1.31
     it
    -1.30
    当日
    -1.30
    POSITIVE LOGITS
    horloge
    1.49
     détermination
    1.45
     FOUR
    1.42
     เมื่อ
    1.42
     شما
    1.36
     grumpy
    1.30
    ított
    1.27
     EIGHT
    1.27
    较
    1.23
    Див
    1.22
    Activations Density 0.021%

    No Known Activations