© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43723
    Prev
    Next
    INDEX
    Explanations

    easy way

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

    This neuron detects words and phrases that signal ease or simplicity (e.g. “easy,” “facili,” “intuitive,” etc.).

    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
    probably
    -1.59
    </strong>
    -1.55
     the
    -1.50
    possibly
    -1.44
     verlangt
    -1.42
    peut
    -1.39
    すごく
    -1.38
     eloquently
    -1.37
    Ꮠ
    -1.35
    particularly
    -1.28
    POSITIVE LOGITS
     easy
    2.28
     easier
    1.84
     Easy
    1.81
    easy
    1.80
    Easy
    1.60
     does
    1.49
     helps
    1.46
     difficult
    1.45
     people
    1.45
     will
    1.45
    Activations Density 0.187%

    No Known Activations