© 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. 104438
    Prev
    Next
    INDEX
    Explanations

    quotation marks and punctuation

    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
    multer
    -0.96
    ERICA
    -0.95
     咖
    -0.94
     voici
    -0.93
     mocking
    -0.88
    JAJA
    -0.87
     dva
    -0.86
     neutron
    -0.86
     bicicleta
    -0.86
     cristianismo
    -0.85
    POSITIVE LOGITS
     ,‬
    1.02
     herrera
    0.94
     noastre
    0.92
    BD
    0.92
    ghum
    0.90
     junit
    0.90
     }^{
    0.90
     "";
    0.90
     travaillent
    0.89
    NING
    0.88
    Activations Density 0.002%

    No Known Activations