© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63784
    Prev
    Next
    INDEX
    Explanations

    product details and series

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

    This neuron fires on low‐frequency (i.e. rare or unusually indexed) tokens in the text.

    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
    確認ください
    -0.96
    ñan
    -0.96
     kuru
    -0.89
     bezit
    -0.87
     remun
    -0.87
    𝙵
    -0.86
    konzert
    -0.86
     Când
    -0.85
     conversely
    -0.83
     передний
    -0.82
    POSITIVE LOGITS
     /
    0.94
     ...
    0.92
    ̶
    0.89
    
    0.88
     microscopy
    0.87
    ↵↵↵↵↵↵
    0.86
    おま
    0.85
    ↵↵↵↵
    0.85
     forêts
    0.84
    ↵↵↵
    0.84
    Activations Density 0.002%

    No Known Activations