© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27778
    Prev
    Next
    INDEX
    Explanations

    UI event code snippets

    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
     more
    -1.05
    Dieu
    -0.97
     and
    -0.96
    ündung
    -0.85
    Menurutnya
    -0.82
    の時に
    -0.82
     all
    -0.81
    alibaba
    -0.80
    ditional
    -0.79
    polation
    -0.79
    POSITIVE LOGITS
    肮
    0.99
    当你
    0.99
    侷
    0.97
    ksiyon
    0.96
    unun
    0.94
     द्वारा
    0.94
    uyasha
    0.93
    áct
    0.93
    不
    0.92
    ATILE
    0.92
    Activations Density 0.014%

    No Known Activations