© 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. 34-GEMMASCOPE-RES-131K
    7. 12258
    Prev
    Next
    INDEX
    Explanations

    visual perception and processing

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

    This neuron highlights technical terms referring to optical and visual‐system components or performance (e.g. resolution, spatial, retina, visual).

    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
     Blaster
    -0.84
     polyethylene
    -0.83
    ื่อน
    -0.81
     صدای
    -0.79
    Vendredi
    -0.79
    fiant
    -0.77
    angé
    -0.77
    haviours
    -0.76
     Aerosol
    -0.76
     stool
    -0.76
    POSITIVE LOGITS
     receptors
    1.31
     receptor
    1.26
     perceiving
    1.20
     perception
    1.05
    receptor
    1.01
     specialized
    0.98
     processing
    0.96
     Receptor
    0.96
     Receptors
    0.95
     detectors
    0.94
    Activations Density 0.070%

    No Known Activations