© 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. 22-GEMMASCOPE-RES-131K
    7. 66030
    Prev
    Next
    INDEX
    Explanations

    importing the errors package

    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_22/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
     vitu
    -1.10
     scelte
    -1.09
     Rá
    -1.09
    特典
    -1.03
     adik
    -1.02
    了不少
    -1.00
    踱
    -0.99
    鑪
    -0.99
    —–
    -0.99
    անի
    -0.98
    POSITIVE LOGITS
     you
    1.37
     or
    1.21
     economics
    1.10
    <strong>
    1.09
     not
    1.09
     calientes
    1.04
     ahora
    1.03
     więc
    1.03
    𝑈
    1.01
    0
    1.00
    Activations Density 0.006%

    No Known Activations