© 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. 129053
    Prev
    Next
    INDEX
    Explanations

    closing tags and explanations

    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
     from
    -1.00
     for
    -0.96
     with
    -0.88
    برز
    -0.87
     bazen
    -0.86
     or
    -0.84
     Australien
    -0.83
    spricht
    -0.83
     yaşında
    -0.83
     aneh
    -0.82
    POSITIVE LOGITS
     explain
    1.23
     explicar
    1.09
     erklä
    1.07
    compromising
    1.05
     expliquer
    1.04
     explained
    1.04
     explanation
    1.01
     Según
    0.99
    PerformLayout
    0.99
     explains
    0.99
    Activations Density 0.025%

    No Known Activations