© 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. 84273
    Prev
    Next
    INDEX
    Explanations

    Purim, KFC, Purified

    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
     This
    -3.41
     beinahe
    -3.41
     gänzlich
    -2.98
     äußerst
    -2.91
     allzu
    -2.89
    with
    -2.81
     erneu
    -2.81
     ziemlich
    -2.80
    但他
    -2.80
     selten
    -2.78
    POSITIVE LOGITS
    ⢓
    2.70
     mikina
    2.53
    芣
    2.48
     可愛い
    2.27
    TacToe
    2.23
    лением
    2.23
     baumwolle
    2.23
     北市
    2.23
    しました
    2.22
     manifeste
    2.16
    Activations Density 0.017%

    No Known Activations