© 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. 34-GEMMASCOPE-RES-131K
    7. 81359
    Prev
    Next
    INDEX
    Explanations

    negative or prohibitive statements

    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_34/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
     dude
    -1.37
    啥
    -1.27
     மற்றும்
    -1.27
     profusely
    -1.17
    dapat
    -1.12
    Anyways
    -1.11
     dudes
    -1.08
     فوت
    -1.05
     рецепт
    -1.05
    咻
    -1.04
    POSITIVE LOGITS
     inside
    1.11
     vincula
    1.05
     elevada
    1.04
     integrado
    1.03
     diverso
    1.00
     returned
    1.00
     choices
    0.99
     mostrare
    0.98
    仍然
    0.98
     dirit
    0.98
    Activations Density 0.019%

    No Known Activations