© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113430
    Prev
    Next
    INDEX
    Explanations

    consent and permission

    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
    ：……
    -1.50
    a
    -1.37
    i
    -1.28
    šanas
    -1.26
     nạ
    -1.25
    ...
    -1.23
     facendo
    -1.21
     Chloride
    -1.20
     делает
    -1.19
     origins
    -1.18
    POSITIVE LOGITS
     of
    2.19
     adonan
    1.51
     orologio
    1.46
    7
    1.42
    甭
    1.41
    érc
    1.39
    8
    1.37
     mattino
    1.36
     soffer
    1.34
     Новости
    1.33
    Activations Density 0.042%

    No Known Activations