© 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. 44683
    Prev
    Next
    INDEX
    Explanations

    sex and sexuality discussion

    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
     ´
    -1.28
     ⠀
    -1.26
     Alguns
    -1.26
    なもの
    -1.25
     aiuta
    -1.24
     Dois
    -1.23
     Bapak
    -1.23
    utentic
    -1.20
    音が
    -1.19
     jeito
    -1.18
    POSITIVE LOGITS
     sentía
    1.31
     You
    1.30
     (!)
    1.20
    اصيل
    1.19
    чкой
    1.19
     sex
    1.19
     by
    1.19
     tasteful
    1.16
    っても
    1.16
     Breite
    1.16
    Activations Density 0.229%

    No Known Activations