© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98227
    Prev
    Next
    INDEX
    Explanations

    so we or and I

    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
    atud
    -0.91
    jenje
    -0.90
    سین
    -0.85
     Kader
    -0.83
    россий
    -0.83
    jande
    -0.82
     bakter
    -0.81
     atras
    -0.81
    اف
    -0.81
     キャ
    -0.80
    POSITIVE LOGITS
     we
    2.09
     will
    1.59
     để
    1.24
     to
    1.23
     We
    1.16
     μας
    1.14
     wtedy
    1.13
     podremos
    1.13
     us
    1.08
     тогда
    1.04
    Activations Density 0.042%

    No Known Activations