© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42424
    Prev
    Next
    INDEX
    Explanations

    male genitalia and undergarments

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    <b>
    -1.16
    ственная
    -1.09
    趼
    -1.08
     udało
    -1.08
    textit
    -1.08
     Например
    -1.06
     легче
    -1.06
    ଢ
    -1.05
     يريد
    -1.05
    起到
    -1.05
    POSITIVE LOGITS
    Véase
    1.33
    童年
    1.27
     are
    1.23
     Wachs
    1.22
    fficking
    1.21
     рослин
    1.19
     unul
    1.17
    ėjas
    1.17
    蹩
    1.16
     навіть
    1.16
    Activations Density 0.071%

    No Known Activations