© 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. 128689
    Prev
    Next
    INDEX
    Explanations

    important to, worry about, happens., while Chris

    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
    Numerous
    -1.07
     both
    -1.06
    Several
    -1.02
     äußerst
    -0.98
    Although
    -0.96
    Diseño
    -0.96
    During
    -0.95
    Both
    -0.93
    Trois
    -0.92
    エディ
    -0.92
    POSITIVE LOGITS
     figlio
    1.03
     your
    1.02
     significa
    1.02
     ziren
    1.01
     befre
    1.00
    спекти
    0.99
     you
    0.99
     davvero
    0.98
     Kräuter
    0.98
     pokrač
    0.97
    Activations Density 0.011%

    No Known Activations