© 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. 74701
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in mente

    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
    ным
    -2.64
     incidence
    -2.39
     sufri
    -2.33
    ೣ
    -2.25
     overriding
    -2.25
    ].
    -2.23
     eradication
    -2.19
    秾
    -2.19
    不妨
    -2.14
     也
    -2.13
    POSITIVE LOGITS
     sement
    2.58
    錒
    2.50
    話は
    2.45
    赁
    2.44
    ～！
    2.38
    ～。
    2.38
    罽
    2.33
     terwijl
    2.31
    蕯
    2.28
    ～♪
    2.27
    Activations Density 0.001%

    No Known Activations