© 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. 65100
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    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
     your
    -1.46
     gimana
    -1.34
    aujourd
    -1.31
     penyanyi
    -1.29
     BOTH
    -1.27
     приеха
    -1.27
     our
    -1.26
     you
    -1.23
    Учитель
    -1.23
     atap
    -1.21
    POSITIVE LOGITS
    娱
    1.31
    melons
    1.15
     during
    1.14
     DOLLARS
    1.13
     suffered
    1.13
    圳
    1.12
     shortly
    1.11
     suffering
    1.10
     гель
    1.09
     for
    1.08
    Activations Density 0.049%

    No Known Activations