© 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. 113106
    Prev
    Next
    INDEX
    Explanations

    Richard followed by name part

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

    The neuron activates on occurrences of the given proper name “Richard.”

    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
    ৢ
    -3.34
     they
    -3.02
     "
    -2.73
    想必
    -2.59
    でない
    -2.59
    恐怕
    -2.55
    卺
    -2.53
     adventures
    -2.48
     anteriormente
    -2.48
    愎
    -2.36
    POSITIVE LOGITS
    </td>
    3.67
    "]));
    2.55
    甡
    2.50
    ｇ
    2.48
    鰾
    2.44
    </i>
    2.42
     maroc
    2.41
     Institut
    2.39
     gial
    2.38
    »،
    2.36
    Activations Density 0.004%

    No Known Activations