© 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. 22-GEMMASCOPE-RES-131K
    7. 75264
    Prev
    Next
    INDEX
    Explanations

    swearing and profanity

    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_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
    lamy
    -1.20
     prendra
    -1.08
    IMENTO
    -1.04
    putBoolean
    -1.03
    也不能
    -1.02
     เส
    -1.02
     stattfinden
    -1.01
     trd
    -1.00
    のための
    -1.00
     réalité
    -1.00
    POSITIVE LOGITS
     use
    1.25
     swearing
    1.23
     not
    1.19
    使用
    1.19
     words
    1.14
    ઞ
    1.13
     language
    1.12
     vocabulary
    1.02
    luğu
    1.02
    罵
    1.01
    Activations Density 0.012%

    No Known Activations