© 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. 15988
    Prev
    Next
    INDEX
    Explanations

    transitions, decays, and production

    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
     السياس
    -1.63
     wirk
    -1.36
     المقبل
    -1.20
    を使って
    -1.19
     obses
    -1.16
     Wikimedijinoj
    -1.12
     APPELLANT
    -1.12
    菟
    -1.09
    控件
    -1.09
     aplicaciones
    -1.09
    POSITIVE LOGITS
     both
    1.27
     sterilization
    1.24
     directly
    1.24
    Groet
    1.18
     these
    1.18
    لقاء
    1.16
     keju
    1.16
     direct
    1.15
    اولة
    1.10
    👡
    1.09
    Activations Density 0.027%

    No Known Activations