© 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. 26521
    Prev
    Next
    INDEX
    Explanations

    UIViewController subclass declarations

    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
     by
    -1.16
    ']),
    -1.05
    SOLVED
    -1.05
    着脸
    -1.01
     mußten
    -0.99
     complesso
    -0.98
     afterwards
    -0.96
    Chaque
    -0.95
    )
    -0.92
    了一会儿
    -0.91
    POSITIVE LOGITS
    ↵↵
    1.05
     была
    0.96
    λεύ
    0.96
     nossa
    0.92
     lorsque
    0.92
    됐
    0.91
    ยม
    0.90
     künf
    0.88
    lå
    0.88
    🉐
    0.88
    Activations Density 0.004%

    No Known Activations