© 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. 73057
    Prev
    Next
    INDEX
    Explanations

    mentioning maiden names

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

    The neuron detects the opening parenthesis that introduces parenthetical information (e.g. birth–death dates or maiden names).

    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
     используется
    -1.16
    例えば
    -1.07
     it
    -1.02
    และ
    -1.00
     אך
    -1.00
    まずは
    -0.98
    且
    -0.96
    比如
    -0.95
    男性
    -0.95
     například
    -0.94
    POSITIVE LOGITS
     oči
    1.03
     with
    1.03
    क्ट
    0.96
     сент
    0.96
    ⬮
    0.91
     МЕ
    0.90
     exe
    0.89
    ność
    0.89
    guém
    0.89
    gemeins
    0.89
    Activations Density 0.018%

    No Known Activations