© 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. 113401
    Prev
    Next
    INDEX
    Explanations

    way of life

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

    The neuron strongly activates on the token “life” (as in “way of life”).

    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
     of
    -4.03
    ſſen
    -2.14
     наших
    -1.73
    峮
    -1.66
     proveniente
    -1.63
    EEE
    -1.56
     
    -1.56
    ✱
    -1.55
    版本的
    -1.55
     должна
    -1.55
    POSITIVE LOGITS
    ,
    1.97
    8
    1.95
    2
    1.94
     in
    1.93
    3
    1.89
     on
    1.86
     those
    1.85
    7
    1.84
    那些
    1.82
     for
    1.80
    Activations Density 0.084%

    No Known Activations