© 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. 22-GEMMASCOPE-RES-131K
    7. 26511
    Prev
    Next
    INDEX
    Explanations

    determination to improve and excel

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

    The neuron fires on words expressing ambition or improvement (e.g., “excel,” “improve,” “determined,” “drive to”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     then
    -1.20
    我會
    -1.09
     or
    -1.07
    很多的
    -1.07
    过多
    -1.06
     escritora
    -1.02
     choosing
    -1.01
     ability
    -0.99
    dibujos
    -0.98
     use
    -0.96
    POSITIVE LOGITS
     what
    1.45
     everyone
    1.10
     everything
    1.09
     suces
    1.01
     things
    1.01
     inaugu
    1.00
     something
    1.00
     whatever
    0.99
     everybody
    0.99
    你知道
    0.97
    Activations Density 0.018%

    No Known Activations