© 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. 26816
    Prev
    Next
    INDEX
    Explanations

    -----BEGIN

    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
     стран
    -1.02
    furl
    -0.96
     удачи
    -0.95
     типа
    -0.94
     able
    -0.94
     ohne
    -0.93
     filtered
    -0.92
    atyana
    -0.91
     leistungs
    -0.88
     resistant
    -0.88
    POSITIVE LOGITS
     and
    1.00
     llevará
    0.94
     Decreased
    0.93
    にぎり
    0.92
    hidupan
    0.92
    הג
    0.91
    diseases
    0.90
    錀
    0.90
    rousel
    0.90
     коме
    0.89
    Activations Density 0.001%

    No Known Activations