© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38470
    Prev
    Next
    INDEX
    Explanations

    receive updates in your inbox

    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
    ävät
    -1.10
     pierdas
    -1.02
    คัญ
    -1.02
     such
    -0.98
     violently
    -0.95
     its
    -0.94
     their
    -0.94
    Ѿ
    -0.93
     dejes
    -0.93
    entibus
    -0.93
    POSITIVE LOGITS
    mopolitan
    1.13
    Masukkan
    1.13
     schuhe
    1.09
     rajut
    1.07
     and
    1.07
     Souhaitez
    1.07
     procesador
    1.06
    Depends
    1.05
     которая
    1.05
     weihnachten
    1.02
    Activations Density 0.001%

    No Known Activations