© 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. 25613
    Prev
    Next
    INDEX
    Explanations

    search bar

    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
    mY
    -1.29
    spes
    -1.26
    muss
    -1.20
    »?
    -1.20
    knew
    -1.18
     Reglas
    -1.16
    montage
    -1.15
    istisches
    -1.14
    .《
    -1.14
    jangan
    -1.14
    POSITIVE LOGITS
     search
    1.48
     searching
    1.29
     pencarian
    1.25
     in
    1.16
     searches
    1.15
     искать
    1.10
    нём
    1.09
    機能
    1.09
     within
    1.08
    search
    1.06
    Activations Density 0.019%

    No Known Activations