© 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. 14230
    Prev
    Next
    INDEX
    Explanations

    genius or Genie references

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

    The neuron strongly activates on mentions of “genius” (and close variants of that root) in text.

    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
     eſſ
    -3.03
    扨
    -2.81
    哢
    -2.75
    谂
    -2.67
    閙
    -2.64
    帏
    -2.61
     juſt
    -2.53
    sieger
    -2.53
    </i>
    -2.52
    珢
    -2.50
    POSITIVE LOGITS
    .
    4.31
     of
    3.86
    Also
    2.56
    In
    2.33
    々は
    2.28
     в
    2.27
     στην
    2.25
     \
    2.25
     en
    2.23
     him
    2.22
    Activations Density 0.006%

    No Known Activations