© 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. 66902
    Prev
    Next
    INDEX
    Explanations

    personal experiences and learning

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

    The neuron activates on occurrences of the word “experience,” flagging mentions of someone’s or something’s experience.

    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
     for
    -2.06
     the
    -1.64
    '
    -1.61
     also
    -1.61
     Для
    -1.52
     内衣
    -1.42
    "+
    -1.37
     outras
    -1.37
    mathrm
    -1.35
     ℃
    -1.35
    POSITIVE LOGITS
     of
    2.06
    s
    1.98
     egreg
    1.60
     dirigeants
    1.51
     immense
    1.48
    described
    1.47
    oping
    1.44
    
    1.42
    hare
    1.41
    病房
    1.39
    Activations Density 0.016%

    No Known Activations