© 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. 12911
    Prev
    Next
    INDEX
    Explanations

    class definition keywords

    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
    ená
    -0.88
     uphe
    -0.88
     it
    -0.84
    ůvod
    -0.84
     foodie
    -0.82
     vorige
    -0.82
     valioso
    -0.81
     potranno
    -0.80
     たち
    -0.80
     绘画
    -0.80
    POSITIVE LOGITS
     ());
    1.03
    我们的
    0.96
    我们
    0.96
    spedes
    0.95
    在这里
    0.94
     אפ
    0.94
     WALKER
    0.93
     mamy
    0.92
     duquel
    0.91
    --;
    0.91
    Activations Density 0.003%

    No Known Activations