© 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. 58634
    Prev
    Next
    INDEX
    Explanations

    Rebecca

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

    The neuron is looking for occurrences of the proper name “Rebecca.”

    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
    𓋼
    -2.64
     wichtige
    -2.44
     frü
    -2.31
    瓛
    -2.31
    
    -2.30
     are
    -2.30
     resurrect
    -2.28
    MenuInflater
    -2.25
    电流
    -2.23
    
    -2.23
    POSITIVE LOGITS
     ‘’
    3.69
    I
    2.75
    It
    2.73
    "));
    2.70
    </td>
    2.67
    </h3>
    2.63
    ”?
    2.55
     ‘‘
    2.48
    ”،
    2.47
     “
    2.39
    Activations Density 0.005%

    No Known Activations