© 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. 59629
    Prev
    Next
    INDEX
    Explanations

    Virgin or Virginia names

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

    The neuron is strongly triggered by occurrences of the word “Virgin” (especially as part of names or titles).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mentions of the “Virgin” root in proper names and titles—especially religious references—along with brand, personal, or species names derived from it.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "Virgin" (especially as a proper noun or in religious/formal contexts).

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    alakip
    -2.63
    縢
    -2.42
    they
    -2.34
     anche
    -2.30
    ⧠
    -2.28
    耜
    -2.27
    或者是
    -2.25
     Genehmigung
    -2.23
    出来ない
    -2.19
     juſ
    -2.19
    POSITIVE LOGITS
    ၞ
    2.56
    .
    2.38
    勠
    2.33
    禵
    2.31
    枼
    2.27
    After
    2.27
    𞤢
    2.17
    A
    2.16
    我先
    2.16
     zaczą
    2.16
    Activations Density 0.009%

    No Known Activations