© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99481
    Prev
    Next
    INDEX
    Explanations

    deve, devo, debo, debería

    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
     offenen
    -2.83
    沨
    -2.78
     vorigen
    -2.75
     siendo
    -2.66
    ᠂
    -2.64
    ’
    -2.52
    WAUKEE
    -2.52
     dangers
    -2.41
    ︲
    -2.36
     behandeln
    -2.34
    POSITIVE LOGITS
    鹮
    3.16
     It
    2.53
    獁
    2.38
     and
    2.16
    絰
    2.14
     如何
    2.06
    貲
    2.00
    注意事
    1.99
     ẞ
    1.89
     bren
    1.84
    Activations Density 0.002%

    No Known Activations