© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7453
    Prev
    Next
    INDEX
    Explanations

    finding a way

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

    The neuron strongly activates on the word “way,” marking occurrences of that exact token.

    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
     you
    -2.67
     outras
    -2.52
     другие
    -2.47
     otras
    -2.22
     autre
    -2.14
     другое
    -2.08
    
    -2.06
     другими
    -2.05
     pressing
    -1.98
    other
    -1.97
    POSITIVE LOGITS
    z
    2.89
    i
    2.78
    n
    2.72
    v
    2.70
    ra
    2.44
     own
    2.42
    j
    2.38
    q
    2.33
    嫱
    2.17
    一些
    2.16
    Activations Density 0.004%

    No Known Activations