© 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. 38557
    Prev
    Next
    INDEX
    Explanations

    competed in or found in

    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
     (
    -1.02
    '],$
    -1.01
    breviations
    -1.01
    ですか
    -0.98
     Zugriff
    -0.94
     |
    -0.94
     $\
    -0.94
     sogenannte
    -0.93
    ḳ
    -0.93
    лько
    -0.92
    POSITIVE LOGITS
    虽说
    1.36
    Lorsque
    1.15
    嗗
    1.08
     próprias
    1.07
    נע
    1.05
    درمان
    1.03
    Masa
    1.00
     it
    1.00
     berpeng
    0.98
     сумка
    0.97
    Activations Density 0.218%

    No Known Activations