© 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. 112939
    Prev
    Next
    INDEX
    Explanations

    being somewhere

    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
    媗
    -1.83
     dénon
    -1.79
    烀
    -1.65
    廡
    -1.63
     também
    -1.62
     semelh
    -1.62
     จาก
    -1.59
     menggunakan
    -1.59
     Ngày
    -1.59
     ſol
    -1.59
    POSITIVE LOGITS
     on
    2.06
     with
    2.00
     for
    1.87
     in
    1.75
     at
    1.73
     enhances
    1.60
     ensuring
    1.59
     facilitates
    1.56
     during
    1.53
     ensures
    1.51
    Activations Density 0.020%

    No Known Activations