© 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. 10-GEMMASCOPE-RES-131K
    7. 66992
    Prev
    Next
    INDEX
    Explanations

    easy to or difficult to

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

    The neuron flags terms that describe how easy or difficult something is (e.g. “easy,” “difficult,” “not impossible”).

    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
    盌
    -1.88
    ᜀ
    -1.83
     diamants
    -1.80
     frança
    -1.78
    狴
    -1.72
     peluche
    -1.71
    
    -1.66
    ༈
    -1.66
     chaqueta
    -1.64
     ſta
    -1.64
    POSITIVE LOGITS
     to
    2.92
     first
    1.81
     if
    1.70
    because
    1.57
     How
    1.57
     Exteriores
    1.41
    Why
    1.39
     даже
    1.38
     porque
    1.37
     What
    1.36
    Activations Density 0.023%

    No Known Activations