© 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. 1185
    Prev
    Next
    INDEX
    Explanations

    festival, festivities, or fiesta

    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
        
    -2.48
     včetně
    -2.36
    т
    -2.34
    ?
    -2.31
     wesentlichen
    -2.22
    こと
    -2.20
    ೢ
    -2.19
     praktischen
    -2.14
    蟜
    -2.14
    器具
    -2.13
    POSITIVE LOGITS
    鹮
    2.73
    and
    2.44
     attire
    2.33
    y
    2.28
    ErrUnexpectedEOF
    2.16
    他的
    2.05
    だったが
    2.03
    ┇
    2.03
    Unlike
    2.02
     میکن
    2.02
    Activations Density 0.002%

    No Known Activations