© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70366
    Prev
    Next
    INDEX
    Explanations

    special characters and web addresses

    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
    引用元
    -1.53
     різних
    -1.39
     from
    -1.35
     out
    -1.34
    發現
    -1.33
     situations
    -1.29
     things
    -1.29
     arduous
    -1.28
     fréquence
    -1.27
    　＊
    -1.27
    POSITIVE LOGITS
     représentent
    1.29
    ichtlich
    1.26
     …
    1.24
    ೨
    1.24
     restent
    1.22
    }}.
    1.20
    ,”
    1.20
    ztes
    1.20
    ).
    1.19
     кари
    1.17
    Activations Density 0.027%

    No Known Activations