© 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. 72818
    Prev
    Next
    INDEX
    Explanations

    obscene, indecent, immoral

    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
     Its
    -1.47
     prioritized
    -1.47
     concluir
    -1.47
     utilized
    -1.45
    帶來
    -1.41
    出来る
    -1.38
     utilised
    -1.34
     permettra
    -1.34
    有り
    -1.27
    说说
    -1.26
    POSITIVE LOGITS
    </u>
    1.37
    Wady
    1.35
     zaten
    1.34
    انگلیسی
    1.34
    Sejarah
    1.32
    Galería
    1.30
     gamle
    1.30
     techniczne
    1.29
     название
    1.25
     normalement
    1.25
    Activations Density 0.034%

    No Known Activations