© 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. 71119
    Prev
    Next
    INDEX
    Explanations

    any word type

    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
    ことなく
    -1.34
     It
    -1.31
    研究院
    -1.27
    為に
    -1.27
    –
    -1.24
     kurzer
    -1.23
    鏽
    -1.19
     zuerst
    -1.18
    ”),
    -1.18
    %;
    -1.16
    POSITIVE LOGITS
     anything
    1.74
     something
    1.60
     a
    1.50
     only
    1.47
     any
    1.38
    Waga
    1.36
     dámské
    1.35
    什么呢
    1.33
    かれています
    1.33
     atlet
    1.30
    Activations Density 0.092%

    No Known Activations