© 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. 25310
    Prev
    Next
    INDEX
    Explanations

    words like masterpiece, door, inspiring

    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
     their
    -1.75
     what
    -1.57
     using
    -1.50
     your
    -1.47
     change
    -1.33
     where
    -1.32
     get
    -1.31
     putting
    -1.31
     zmienia
    -1.29
     from
    -1.26
    POSITIVE LOGITS
    Vendredi
    1.34
    Dimanche
    1.28
     conster
    1.28
     leher
    1.27
     chanti
    1.27
    ↑↑↑
    1.25
    Samedi
    1.25
    それにしても
    1.24
    Entrevista
    1.24
     applau
    1.23
    Activations Density 0.003%

    No Known Activations