© 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. 113434
    Prev
    Next
    INDEX
    Explanations

    regarding, cause, slicing

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

    The neuron selectively activates on the word “regards,” flagging instances of that 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
    试图
    -1.93
    atedral
    -1.73
    .
    -1.70
     colorido
    -1.68
    What
    -1.66
    );
    -1.65
    姈
    -1.63
     verbinding
    -1.62
     efekt
    -1.60
     "
    -1.59
    POSITIVE LOGITS
     Moreover
    1.98
     Also
    1.86
     Además
    1.82
     figlio
    1.78
    𝗿
    1.73
     edifici
    1.71
    ations
    1.71
    ur
    1.70
     alberi
    1.70
     naprawdę
    1.67
    Activations Density 0.001%

    No Known Activations